Context files
The shelf: every file an agent can load, filed under the concept it belongs to and sized in tokens.
Context files is for loading: each row below is a plain markdown file — a concept's facts file — and the link on it is the file itself. Click a root or a concept name to expand it in place; nothing here navigates except the file links.Concepts is the other tab: the same research as a map you browse.
A facts file is one concept's facets and facts as a markdown list, each fact carrying the URL it came from. How these files are filed and formatted. Agents: fetch /context.md for this whole listing as one file; any row below is the second and last hop.
1823 concepts · 94,593 facts in 11,583 facets · 36 roots · generated 2026-10-24
AI & LLM Engineering762 concepts
16 GB VRAM residency budgeting7 facts · 3 facets
3D/ND parallelism composition (TP×PP×CP×EP×DP placement) + expert parallelism41 facts · 6 facets
7-State Task Lifecycle53 facts · 6 facets
A2A Protocol Interoperability31 facts · 9 facets
AAIF and Protocol Governance62 facts · 7 facets
Acceptance drift of a base MTP head on a distilled trunk18 facts · 2 facets
Adaptive block-size scheduling for DFlash at inference12 facts · 2 facets
AFM 3 and ADM model family architecture evolution13 facts · 4 facets
Agent Council14 facts · 6 facets
Agent Harness Construction25 facts · 9 facets
Agent harnesses on Ollama: OpenClaw / Hermes Agent / Goose / Pi78 facts · 8 facets
Agent Identity, Authorization & Payments107 facts · 21 facets
Agent Memory Architecture2 facts · 1 facets
Agent Plan Writing37 facts · 8 facets
Agent Planning & Control-Flow Patterns2 facts · 1 facets
Agent Reliability & Guardrails2 facts · 1 facets
Agent Runtime Sandboxes & Code Execution88 facts · 17 facets
Agent skill-listing injection cost68 facts · 2 facets
Agent State & Durable Execution85 facts · 20 facets
Agent-owned KV cache export import artifacts16 facts · 1 facets
Agentic and Advanced RAG Patterns125 facts · 20 facets
Agentic RL — Reinforcement Learning for LLM Agents102 facts · 21 facets
agents.md and the Universal Commerce Protocol (UCP)103 facts · 9 facets
Aggregate SSD bandwidth when each cluster node streams experts36 facts · 2 facets
AI Agent Ecosystems26 facts · 7 facets
AI Coding-Agent Design125 facts · 21 facets
AI Datastores1 facts · 1 facets
AI Gateways & LLM Proxy Infrastructure109 facts · 24 facets
AI Programming Languages19 facts · 5 facets
AI Red-Teaming and Security-Testing Tooling125 facts · 22 facets
Aider in Open-Source Agentic Coding with Ollama92 facts · 15 facets
Air-gapped Ollama deployment and model mirroring85 facts · 10 facets
Allocation path behind MTLResourceStorageModeShared buffers (IOGPU vs IOSurface)5 facts · 1 facets
ANE dispatch and IOSurface round-trip overhead in small decode graphs16 facts · 1 facets
ANE numerics hazards in FP1685 facts · 2 facets
ANE SRAM 32 MB cliff and graph-depth utilization13 facts · 1 facets
ANE SRAM cliff for 1x1 conv and decode-shaped tensors34 facts · 1 facets
ANE weight-read bandwidth by chip58 facts · 1 facets
ANE-prefill plus GPU decode hybrid inference53 facts · 2 facets
ANEMLL ANE LLM conversion pipeline83 facts · 2 facets
Anthropic-compatible local endpoints and mid-conversation role system messages86 facts · 1 facets
Apple Foundation Models framework108 facts · 2 facets
Apple foundation-models-utilities ChatCompletionsLanguageModel70 facts · 2 facets
Apple libthunderboltrdma tbt_post_recv SIGSEGV16 facts · 1 facets
Apple NVMe small random read latency under F_NOCACHE at queue depth 168 facts · 1 facets
Apple silicon memory bandwidth and decode speed by chip79 facts · 1 facets
Apple Silicon SSD SMART telemetry and Percentage Used interpretation31 facts · 1 facets
Apple silicon unified memory and LLM sizing102 facts · 2 facets
Apple SSD speed dependence on NAND capacity and package count26 facts · 1 facets
Apple UC send into a queue pair with no posted receive kills that direction7 facts · 1 facets
apple-silicon-llm-bench fairness rules and interleaved-arm protocol41 facts · 1 facets
Application-level no-progress watchdog and group re-formation for JACCL clusters48 facts · 1 facets
ASUS NUC BIOS Thunderbolt options and the iSetupCfg CLI72 facts · 11 facets
Atlas Query Insights, Performance Advisor and Compass explain760 facts · 9 facets
Autonomous Loop Patterns81 facts · 35 facets
Benchmark methodology pitfalls for local LLM runtimes57 facts · 1 facets
BFCL and tool-calling evals for quantized local models22 facts · 1 facets
Bitemporal claim provenance15 facts · 3 facets
Blackwell sm_120 local-LLM inference stack on Linux: llama.cpp, Ollama, PyTorch and vLLM over a Thunderbolt eGPU131 facts · 22 facets
Branch-and-follow flip analysis harness for Mac GGUF and MLX quants38 facts · 1 facets
CachyLlama llama.cpp fork with persistent KV19 facts · 1 facets
Calibration-set contamination and held-out evaluation corpora20 facts · 1 facets
Candidate-depth-aware hybrid rank fusion21 facts · 3 facets
Chat-template and tool-declaration determinism as a cache-hit prerequisite26 facts · 1 facets
Chat-template patching for cache stability24 facts · 1 facets
Checkpointing & state persistence55 facts · 6 facets
Citation entailment for generated research prose20 facts · 4 facets
Claude Code compaction floor of 100K versus small local windows6 facts · 1 facets
Claude Code context-window mismatch against local servers65 facts · 1 facets
Claude Code effort levels forwarded to local Anthropic-compatible servers25 facts · 1 facets
Claude Code gateway hint headers for local routers17 facts · 1 facets
Claude Code helper-model request to custom base URL17 facts · 1 facets
Claude Code Plugins22 facts · 8 facets
Claude Code reactive compaction error-wording recognition17 facts · 1 facets
Claude Code skill listing budget formula5 facts · 1 facets
Claude Code Skills30 facts · 9 facets
Claude Code system-prompt and tool-schema slimming for local models67 facts · 1 facets
Claude Code unknown-model context window handling1 facts · 1 facets
claude-code-router Anthropic-to-OpenAI translation over a local gateway21 facts · 1 facets
CLAUDE_CODE_SUBAGENT_MODEL routing of subagents to a small local model15 facts · 2 facets
Client-side compaction thresholds for hybrid-model local servers19 facts · 1 facets
Cloudflare AI-crawler monetization & verification stack107 facts · 8 facets
Codex auto-compaction body_after_prefix scope10 facts · 1 facets
Codex model catalog JSON (model_catalog_json) for local model slugs33 facts · 1 facets
Codex model-visible tool exposure rules (spec_plan.rs namespace_tools capability16 facts · 2 facets
Codex namespace and hosted tool types skipped by local servers15 facts · 2 facets
Codex provider capabilities struct and where namespace serialization is gated14 facts · 1 facets
Codex Responses API compatibility on local servers25 facts · 1 facets
Codex tool_search deferred MCP tools and the supports_search_tool catalog flag16 facts · 1 facets
Computer-Use & GUI Agents2 facts · 1 facets
Concept knowledge architecture strategies129 facts · 6 facets
Conceptual Family Exploration80 facts · 21 facets
Confidence-conditioned top-1 flip rate for literal-copy tokens37 facts · 2 facets
Context shift and cache-overflow policy for recurrent models21 facts · 1 facets
Context Sizing Budgets on 16GB VRAM2 facts · 1 facets
Context-preserving multi-granularity embeddings15 facts · 3 facets
Context-Window Pressure & Compaction44 facts · 6 facets
Continuous batching and aggregate throughput on MoE3 facts · 1 facets
Continuous batching and concurrent-request serving on Apple silicon3 facts · 1 facets
Continuous batching on MLX77 facts · 2 facets
Continuous Learning System29 facts · 7 facets
Core AI framework70 facts · 2 facets
Core ML and Apple Neural Engine for LLMs62 facts · 2 facets
Core ML stateful KV-cache compile constraints39 facts · 2 facets
Core ML to MLX KV cache hand-off cost and layout35 facts · 1 facets
CoreML-LLM john-rocky ANE LLM runtime37 facts · 1 facets
Cost of a mincore sweep per GB on Apple silicon23 facts · 1 facets
Cross-Encoder Re-ranking vs Bi-Encoders for Terminal Validation in RAG and Deduplication43 facts · 12 facets
Cross-engine reference logits precision and tokenizer parity39 facts · 1 facets
Cross-layer attention (CLA) KV sharing31 facts · 1 facets
Data-driven mixed-precision MLX quants (oQ, OptiQ, JANG)99 facts · 2 facets
Declarative and Programmatic LLM Frameworks120 facts · 28 facets
Deep Research98 facts · 18 facets
Deep Research Methods115 facts · 32 facets
Dense vs MoE MLX vs llama.cpp decode on Apple silicon48 facts · 1 facets
Dependent-chain versus queue-batched MLX kernel benchmarking27 facts · 1 facets
Depth policy that measures draft and verify cost per depth19 facts · 1 facets
DFlash and DDTree speculative decoding drafters31 facts · 1 facets
DFlash block-diffusion drafters on hybrid targets in llama.cpp (PR 22105)48 facts · 1 facets
DFlash image-input position gap in llama.cpp draft context33 facts · 1 facets
Diagnosing a GPU that has fallen off the bus: config space, MMIO chip ID and AER105 facts · 25 facets
Diffusion & Generative-Media Models70 facts · 18 facets
Disk and SSD-tiered KV cache servers126 facts · 2 facets
Distributed inference across Macs99 facts · 2 facets
Distributed Training & Training Infrastructure43 facts · 8 facets
Diversity-restoring decoding and prompting5 facts · 3 facets
Docker Model Runner68 facts · 6 facets
Draft length tuning (spec-draft-n-max) for block-diffusion drafters32 facts · 1 facets
ds4 antirez SSD streaming runtime50 facts · 1 facets
ds4 decode-time Engram read latency on Apple SSD (48 random reads per token)29 facts · 1 facets
ds4 disk KV cache and SHA1 byte-prefix keying48 facts · 1 facets
ds4 layer pipeline parallelism over TCP with activation quantization34 facts · 1 facets
ds4 manual cache safe-bytes cap (7/8 of recommended working set minus context)1 facts · 1 facets
ds4 own verbs layer versus JACCL28 facts · 1 facets
ds4 streaming expert cache sizing under TP10 facts · 1 facets
ds4 TP big-gate bulk exchange for prefill over RDMA9 facts · 1 facets
ds4 TP gate chunking and 16-gate receive lookahead window37 facts · 1 facets
ds4 TP speculative-verify block window over RDMA (tag 0xB5)1 facts · 1 facets
ds4 TP with --ssd-streaming on Metal for GLM and V4.124 facts · 1 facets
ds4 two-Mac tensor parallelism over Thunderbolt RDMA setup42 facts · 1 facets
Durable Agent Execution & Long-Running Agent Runtimes110 facts · 26 facets
Dynamic Profiles historyTransform12 facts · 1 facets
Editor integrations for Ollama: Continue / Cline / Roo Code / Zed / JetBrains / VS Code81 facts · 7 facets
Effect of the 16-nat logit clamp in the .kld encoder on tail KLD20 facts · 2 facets
Effective bits-per-weight and size confounds in MLX N-bit quant names29 facts · 1 facets
Emphatic language in prompts and overtriggering6 facts · 3 facets
Energy per token measurement on Apple Silicon52 facts · 2 facets
Engram and n-gram embedding tables read from disk per token17 facts · 1 facets
Engram row prefetch overlapped with preceding transformer blocks in Mac runtimes17 facts · 1 facets
EU AI Act Article 53(1)(c) TDM Opt-Out64 facts · 12 facets
Eval-Driven Development for LLM Apps99 facts · 19 facets
Exact tool-call replay for byte-stable agent prefixes23 facts · 1 facets
exo cluster software117 facts · 1 facets
exo DeepSeek V4 expert sharding (ShardedMoEV4) as EP substitute32 facts · 2 facets
exo MLX_METAL_FAST_SYNCH only for RDMA instances (exo PR 2377)26 facts · 1 facets
exo orphaned runner holds RDMA queue pairs (RTR errno 16)23 facts · 2 facets
exo pinned MLX fork7 facts · 1 facets
exo PR 2348 plan loop no longer waits for generation task acknowledgement3 facts · 1 facets
exo prefill/decode disaggregation12 facts · 2 facets
exo ring-abort detection by stderr diagnostic (PR 2367)29 facts · 1 facets
exo set_rdma_network_config.sh network setup script31 facts · 1 facets
exo stuck-runner 90-second no-progress watchdog (PR 2370)31 facts · 1 facets
exo vs mlx.launch tensor-parallel throughput controlled comparison52 facts · 2 facets
Expert overlap between draft tokens in MoE speculative verification33 facts · 2 facets
Expert-cache policy and on-disk layout for MoE streaming45 facts · 1 facets
Expert-count reduction at inference top-k override36 facts · 1 facets
Expert-deduplicating gather kernels for verify windows on Metal24 facts · 1 facets
Extraction Evaluation Frameworks52 facts · 19 facets
fdesetup authrestart and FileVault pre-boot unlock for headless Macs27 facts · 1 facets
First Divergent Token metric rollouts on GGUF and MLX quants2 facts · 1 facets
Flash-MoE paper flash_moe.pdf 90+ experiment log46 facts · 2 facets
Flash-MoE SSD-streamed MoE expert runtime38 facts · 1 facets
Flattening proxies for Codex namespace tools (codex-ollama-proxy and similar)26 facts · 2 facets
fm serve and the fm CLI OpenAI-compatible endpoint3 facts · 2 facets
Foundation Models adapter lifecycle across OS releases9 facts · 3 facets
Foundation Models context and error version reconciliation11 facts · 4 facets
Foundation Models evaluation and OS regression workflow20 facts · 5 facets
Foundation Models guardrails and untrusted input boundaries14 facts · 4 facets
Foundation Models multimodal input and capability contracts10 facts · 5 facets
Foundation Models PCC eligibility quotas and migration11 facts · 3 facets
Foundation Models provider interoperability and release status11 facts · 1 facets
FP16 attention partial-sum overflow in split attention kernels on M1 and M225 facts · 1 facets
Gemma 3/4 float16 activation overflow handling across runtimes36 facts · 1 facets
Gemma 4 31B GGUF quants ranked by KL divergence24 facts · 1 facets
Gemma 4 attention_k_eq_v global-layer key-as-value sharing10 facts · 1 facets
Gemma 4 float16 conversion guard for M1/M2 MLX28 facts · 1 facets
Gemma 4 mobile-mixture QAT with TQ2_0 2-bit layers (UD-Q2_K_XL for E2B/E4B)1 facts · 1 facets
Gemma 4 QAT GGUF conversion: F16 versus BF16 scales in llama.cpp Q4_021 facts · 1 facets
Gemma 4 shared KV cache layers YOCO8 facts · 2 facets
Gemma 4 sliding-window layer exclusion from KV quantization5 facts · 2 facets
Gemma 4 thought stripping in agentic turns10 facts · 1 facets
Gemma 4 vision tower standardize overflow and mmproj dtype on Metal27 facts · 1 facets
Gemma-4 assistant drafters on MLX and llama.cpp33 facts · 1 facets
Gemma4ClippableLinear input/output clamp scalars in the mmproj7 facts · 1 facets
Generation-drift metrics beyond prefill KLD40 facts · 1 facets
GGUF re-upload versioning and stale cache hygiene49 facts · 1 facets
GGUF tensor reordering script with gguf-py plus hash verification15 facts · 1 facets
gpt-oss Harmony reasoning replay across tool calls17 facts · 1 facets
GPU & Accelerator Kernels for LLMs130 facts · 23 facets
GPU firmware lockup reports gpuEvent ips34 facts · 1 facets
GPU hot-unplug and surprise-removal safety for a Thunderbolt eGPU on Linux79 facts · 13 facets
GPU-written no-copy buffer footprint charging13 facts · 2 facets
GQA KV Cache Memory Mechanics3 facts · 3 facets
Grafting a base model's MTP head onto a fine-tuned trunk (MiMo-V2.6 distill)29 facts · 2 facets
Grammar-aware draft filtering for ngram and draft-model drafters5 facts · 1 facets
guruswami-ai mlx-benchmarks cluster dataset12 facts · 1 facets
Hardware-calibrated verification budget for batch-wide tree speculation29 facts · 1 facets
Head-to-head top-40 versus full-vocabulary KLD on one model and text1 facts · 1 facets
Headless Apple silicon Mac virtual display and the interactivity watchdog22 facts · 2 facets
Health monitoring, alerting and safe automated recovery for a Thunderbolt eGPU100 facts · 13 facets
Heart121 facts · 7 facets
Heuristic Boilerplate Removal & Text-Density Algorithms for Web Extraction51 facts · 17 facets
Hook additional-context injection into the first message19 facts · 1 facets
Hook-based filtering of agent output5 facts · 2 facets
Hybrid and recurrent model checkpoint handling in oMLX21 facts · 1 facets
Hybrid and sliding-window attention KV cache rewinding93 facts · 2 facets
Hybrid GatedDeltaNet state rollback and checkpoint prefix caching24 facts · 1 facets
Hybrid graphics on Linux: Intel iGPU plus NVIDIA eGPU for headless compute63 facts · 11 facets
Hybrid Mamba-2 and MoE model support across Mac runtimes14 facts · 1 facets
Hybrid Score Fusion (Reciprocal Rank Fusion - RRF)37 facts · 11 facets
IAM Role Atlas API Access15 facts · 3 facets
ibv_devinfo hang as an RDMA health probe20 facts · 1 facets
Idle power and energy accounting for an always-on Thunderbolt eGPU60 facts · 13 facets
Importance-matrix presence as a second axis in equal-size KLD comparisons8 facts · 1 facets
Instruction-file hygiene for LLM lexical tics: linting, mirroring, hook filtering29 facts · 5 facets
Inter-model homogeneity in open-ended generation6 facts · 4 facets
IOGPUFamily driver bug and userspace panic mitigations such as MetalGuard73 facts · 1 facets
IOKit-mapped Metal buffer accounting in phys_footprint22 facts · 2 facets
IOReport Energy Model channels versus powermetrics samplers36 facts · 2 facets
Isolated Metal microbenchmark of Q6_K vs Q4_K mat-vec at matched bytes10 facts · 1 facets
Iterative Retrieval38 facts · 12 facets
JACCL coordinator-optional connection setup (mlx PR 3899)28 facts · 1 facets
JACCL GID selection regression and RTR errno 22 (mlx 3467)40 facts · 2 facets
JACCL mesh versus ring topology selection and per-pair device counts2 facts · 2 facets
JACCL MeshImpl all_reduce race fix mlx 345130 facts · 2 facets
JACCL peer-liveness side channel and progress timeout PR 453017 facts · 2 facets
JACCL protection domain exhaustion on repeated mx.distributed.init8 facts · 1 facets
JACCL RDMA completion status checking and silent corruption11 facts · 2 facets
JACCL ring all_gather direction-1 slice bug (mlx PR 4443)27 facts · 1 facets
JACCL ring all_reduce wire partitioning (n_wires, directions, threads)13 facts · 1 facets
JACCL RTR sgid_index hard-coded to 120 facts · 2 facets
JACCL silent hang on peer loss17 facts · 1 facets
JACCL TCPAllGather side channel as peer-liveness channel6 facts · 1 facets
JangPress cold-expert eviction for MoE larger than RAM39 facts · 2 facets
JangPress RSS accounting after expert deactivation on macOS22 facts · 1 facets
Jinja templates failing on llama.cpp engine but passing in Python30 facts · 1 facets
KLD-based quant evaluation methodology84 facts · 1 facets
KV cache and long context on Mac114 facts · 2 facets
KV cache quantization (4-bit and 8-bit) memory pricing and NaN failures in MTPLX16 facts · 1 facets
KV cache quantization tradeoffs on Apple GPUs96 facts · 2 facets
KV checkpoint eviction scoring by tokens per byte with hit decay26 facts · 2 facets
KV-cache quantization degrading tool-call accuracy21 facts · 1 facets
KV-cache quantization effect on tool-call flips (int8 vs int4)37 facts · 2 facets
LangChain and LlamaIndex integrations with Ollama37 facts · 6 facets
launchd ExitTimeOut and graceful stop discipline for large MLX models4 facts · 2 facets
launchd service setup for local LLM servers80 facts · 2 facets
LCKV and YOCO cross-layer KV sharing variants17 facts · 1 facets
Linting instruction files for seeded vocabulary6 facts · 4 facets
Linux thunderbolt driver: host_reset, CLx and bolt authorization104 facts · 19 facets
LiteLLM Anthropic Messages interoperability12 facts · 6 facets
LiteLLM Anthropic-to-Chat-Completions translation bugs for Claude Code16 facts · 1 facets
LiteLLM local Ollama and OpenAI-compatible backends12 facts · 5 facets
LiteLLM observability and caching12 facts · 4 facets
LiteLLM proxy deployment and configuration12 facts · 6 facets
LiteLLM routing retries and fallbacks11 facts · 5 facets
LiteLLM SDK provider normalization12 facts · 6 facets
LiteLLM tool calls and SSE streaming12 facts · 7 facets
LiteLLM virtual keys budgets and rate limits12 facts · 7 facets
llama serve command (router-mode daemon front end)3 facts · 1 facets
llama-fit-params tool and freezing fitted flags into a launch script21 facts · 1 facets
Llama-macOS menu-bar app74 facts · 1 facets
llama-quantize --tensor-type-file recipes for MoE shared experts42 facts · 1 facets
llama-quantize --tensor-type-file role-aware policies (attention/FFN/boundary)40 facts · 1 facets
llama-server --load-mode dio and lazy-mode on Apple silicon39 facts · 2 facets
llama-server --video-fps, --video-timestamp-interval and --video-ffmpeg-dir flag1 facts · 1 facets
llama-server /props n_ctx as the per-slot window to advertise to clients10 facts · 1 facets
llama-server host-memory prompt cache and idle sleep unload37 facts · 2 facets
llama-server readiness and health semantics after fatal Metal init OOM29 facts · 1 facets
llama-server router child bind address versus router --host12 facts · 2 facets
llama-server router mode child instance exposure and auth15 facts · 1 facets
llama-server router subprocess build option (subprocess is not enabled on this b19 facts · 1 facets
llama-server slot and unified-KV configuration26 facts · 1 facets
llama-swap lifecycle hooks and wrapper-based KV save restore73 facts · 1 facets
llama.cpp --fit auto memory fitting74 facts · 1 facets
llama.cpp --mtmd-batch-max-tokens tuning against n_ubatch for non-causal project1 facts · 1 facets
llama.cpp --sleep-idle-seconds router sleeping state keeps its models-max slot40 facts · 1 facets
llama.cpp --spec-default and low-acceptance streak reset (PRs 22223 and 22168)32 facts · 1 facets
llama.cpp .kld reference file binary layout and external reader21 facts · 1 facets
llama.cpp attention rotation Hadamard for quantized KV cache7 facts · 2 facets
llama.cpp autoparser analyze_reasoning, analyze_content and analyze_tools diff p20 facts · 1 facets
llama.cpp autoparser workaround lambdas in chat-diff-analyzer.cpp15 facts · 1 facets
llama.cpp build-number drift in published Mac benchmarks25 facts · 1 facets
llama.cpp bundled revision inside Ollama releases39 facts · 1 facets
llama.cpp causal_attn flag scheduler re-reserve cost per image (PR 28751)19 facts · 1 facets
llama.cpp chat.cpp per-template regex rewrites versus Jinja input marking25 facts · 1 facets
llama.cpp context checkpoint 64-token minimum tuning26 facts · 1 facets
llama.cpp context checkpoints and SWA hybrid prompt re-processing38 facts · 2 facets
llama.cpp default port change to 993126 facts · 2 facets
llama.cpp EAGLE-3 and DSpark speculator drafters46 facts · 1 facets
llama.cpp gemma4uv projector type support and first supporting build20 facts · 1 facets
llama.cpp host prompt cache interaction with id_slot pinning13 facts · 1 facets
llama.cpp host-memory prompt cache cache-ram cache-idle-slots on unified memory14 facts · 1 facets
llama.cpp jinja capability probes chat_template_caps42 facts · 1 facets
llama.cpp Jinja input marking is_input special-token injection defence31 facts · 1 facets
llama.cpp Jinja runtime (minja replacement) tojson and filter semantics20 facts · 1 facets
llama.cpp lazy-mode lazy tensor reading of oversized embedding tables18 facts · 1 facets
llama.cpp message_spans chat-template user-boundary detection for checkpoints26 facts · 1 facets
llama.cpp Metal backend on Mac100 facts · 2 facets
llama.cpp MoE tensor-API port7 facts · 1 facets
llama.cpp mtmd batching of consecutive image chunks into one non-causal decode11 facts · 1 facets
llama.cpp mtmd lazy bitmaps for frame-by-frame video4 facts · 1 facets
llama.cpp mtmd video and webp input via ffmpeg subprocess (MTMD_VIDEO, PR 27520)11 facts · 1 facets
llama.cpp ngram-mod and ngram-map-k4v drafter internals21 facts · 1 facets
llama.cpp ngram-mod speculative stuck loop (issue 23268, PR 25819)34 facts · 2 facets
llama.cpp normalisation of Claude Code billing header cch13 facts · 1 facets
llama.cpp PR 25309 sparse mmap tensor range coalescing33 facts · 1 facets
llama.cpp PR 25592 exact-position hybrid checkpoint restore18 facts · 2 facets
llama.cpp prompt-cache eviction when cache-ram limit is hit31 facts · 1 facets
llama.cpp reasoning-budget sampler and lazy grammar trigger gating7 facts · 1 facets
llama.cpp reasoning-preserve flag and template support detection11 facts · 2 facets
llama.cpp reasoning-preserve vs Qwen preserve_thinking template key aliasing33 facts · 2 facets
llama.cpp Responses SSE event ordering and reasoning items15 facts · 1 facets
llama.cpp RPC -sm tensor PR 2661015 facts · 2 facets
llama.cpp seq_pos_min hybrid memory fix PR 2479733 facts · 2 facets
llama.cpp slot state trimming when the template will drop reasoning26 facts · 1 facets
llama.cpp speculative checkpointing for hybrid models (PRs 19493 and 22227)38 facts · 1 facets
llama_n_ctx_seq semantics with and without unified KV9 facts · 1 facets
LLAMA_SERVER_SLOTS_DEBUG mismatch logging workflow25 facts · 1 facets
LlamaParse vs. Docling for LLM Ingestion38 facts · 10 facets
LLM Alignment and Post-Training2 facts · 1 facets
LLM Compression (Quantization, Distillation, Pruning, Merging)2 facts · 1 facets
LLM Context Engineering99 facts · 20 facets
LLM Fine-Tuning & PEFT137 facts · 27 facets
LLM Inference Optimization and Serving154 facts · 19 facets
LLM Model Routing, Cascades & Mixture-of-Agents31 facts · 5 facets
LLM Models and APIs18 facts · 5 facets
LLM Observability2 facts · 1 facets
LLM Pretraining & Scaling Laws127 facts · 21 facets
LLM Zero-Shot Data Extraction for Unstructured Text43 facts · 13 facets
LLM-as-judge bias & calibration (kappa, binary-vs-Likert, position/verbosity/self-preference)72 facts · 7 facets
llm-benchpacks workload-level agent benchmarks37 facts · 1 facets
llms.txt60 facts · 7 facets
LM Studio MLX engine92 facts · 2 facets
LM Studio on Mac72 facts · 1 facets
Loading an eGPU driver after bolt with systemd109 facts · 16 facets
Local embeddings from Ollama into MongoDB Atlas Vector Search22 facts · 6 facets
Local LLM model load path over a Thunderbolt eGPU98 facts · 13 facets
Local LLM server as a coding-agent backend on Mac125 facts · 2 facets
Local router policy keyed on x-claude-code-request-class27 facts · 1 facets
LocalAI102 facts · 10 facets
localbench top-40 union KL estimator versus .kld full-vocab KLD16 facts · 1 facets
Log-log size-to-KLD elasticity of K-quants across model families16 facts · 1 facets
Long-running MLX server OOM recovery and process recycling44 facts · 1 facets
Loop & No-Progress Detection54 facts · 6 facets
LoRA adapters in Ollama via ADAPTER49 facts · 7 facets
M1/M2 software-emulated bfloat16 and FP16 conversion55 facts · 1 facets
M5 GPU TF32 numerics and batched attention divergence50 facts · 2 facets
M5 Max watchdogd 90 s kernel panic under sustained GPU load34 facts · 1 facets
M5 NAX tensor-unit kernels in MLX servers33 facts · 1 facets
Mac local LLMs: Agent clients, context and compaction66 facts · 10 facets
Mac local LLMs: ANE and Core ML LLMs54 facts · 11 facets
Mac local LLMs: Apple Foundation Models and Core AI49 facts · 9 facets
Mac local LLMs: Benchmarking and comparisons52 facts · 10 facets
Mac local LLMs: Chat templates, reasoning and tool calling67 facts · 9 facets
Mac local LLMs: Clusters, RDMA, exo and ds493 facts · 9 facets
Mac local LLMs: GPU stability and kernel panics48 facts · 10 facets
Mac local LLMs: KV cache sizing and quantization70 facts · 9 facets
Mac local LLMs: llama.cpp internals64 facts · 10 facets
Mac local LLMs: Memory and wired limits74 facts · 11 facets
Mac local LLMs: MLX kernels, numerics and internals61 facts · 11 facets
Mac local LLMs: MoE streaming and offload61 facts · 10 facets
Mac local LLMs: Ollama internals44 facts · 12 facets
Mac local LLMs: oMLX, Rapid-MLX and related internals55 facts · 13 facets
Mac local LLMs: Prompt cache and persistent KV66 facts · 9 facets
Mac local LLMs: Quantization evaluation56 facts · 11 facets
Mac local LLMs: Quantization formats and methods55 facts · 12 facets
Mac local LLMs: Runtime selection and frontends49 facts · 9 facets
Mac local LLMs: Serving ops and multi-model56 facts · 9 facets
Mac local LLMs: Speculative decoding and MTP82 facts · 13 facets
Mac local LLMs: Speed, bandwidth and prefill55 facts · 10 facets
macOS 26.2 stops self-assigning IPv4 on Thunderbolt RDMA interfaces18 facts · 1 facets
macOS 27 IOGPUFamily changes and whether the panic is fixed41 facts · 1 facets
macOS 27 libthunderboltrdma rework4 facts · 1 facets
macOS 27 TensorOps FP8 FP4 MX scale planes32 facts · 1 facets
macOS memory compressor thrashing from GPU-visible buffers24 facts · 1 facets
macOS memorystatus and jetsam behavior on non-iOS Macs under memory pressure29 facts · 2 facets
macOS network service order and Thunderbolt Bridge auto-creation on upgrade1 facts · 1 facets
macOS no_paging_space_action Out of Application Memory dialog16 facts · 1 facets
macOS swap and compressed memory write behavior under memory pressure36 facts · 1 facets
macOS Tahoe GPU command-buffer hangs55 facts · 1 facets
macOS TCC Files and Folders consent for boot-time daemons31 facts · 1 facets
macOS unified buffer cache policy and wired memory interaction30 facts · 2 facets
macOS vm pressure level thresholds kVMPressureWarning and kVMPressureCritical24 facts · 1 facets
macOS vm.user_wire_limit and RLIMIT_MEMLOCK for mlock23 facts · 1 facets
macOS wired memory limit and GPU kernel panics114 facts · 1 facets
maderix reverse-engineered ANE hardware profile41 facts · 1 facets
MADV_DONTNEED on file-backed mmap semantics on macOS36 facts · 2 facets
Marginal evidence gain research stopping19 facts · 3 facets
MCP Server Builder Patterns123 facts · 15 facets
MCP Server Development31 facts · 9 facets
MCP tool-definition token cost in OpenCode81 facts · 1 facets
mcp-compressor wrapper proxy in front of a local-model agent6 facts · 1 facets
Measuring a Thunderbolt eGPU: bandwidth, latency and inference benchmarks88 facts · 16 facets
Mechanistic Interpretability83 facts · 18 facets
Metal 4 tensor API and M5 Neural Accelerator prefill in llama.cpp57 facts · 1 facets
Metal attention multi-row verify cliff at 6-15 query rows33 facts · 2 facets
Metal flash attention K.type==V.type constraint1 facts · 1 facets
Metal flash-attention kernel partitioning differences across M-series chips61 facts · 2 facets
Metal GPU hangs with multiple concurrent engines in one process40 facts · 1 facets
Metal GPU watchdog 5 s timeout in distributed MLX generation10 facts · 2 facets
Metal mmap span mapping and residency-set wiring for partial offload53 facts · 1 facets
Metal newBufferWithBytesNoCopy file-cache-backed weights refault4 facts · 1 facets
Metal prefill cost of Q8_0 shared experts beside Q4_K routed experts15 facts · 1 facets
Metal residency sets and llama.cpp Metal internals79 facts · 1 facets
MetalGuard user-space GPU-crash mitigations42 facts · 1 facets
Microsoft Foundry Local107 facts · 9 facets
mincore MINCORE_PAGED_OUT probe for compressor residency of Metal buffers19 facts · 1 facets
mincore residency probing of mmap'd model weights on macOS31 facts · 1 facets
Mixed-precision KV-cache quantization per-layer sensitivity9 facts · 1 facets
Mixed-precision quantization for MoE experts 4-bit attention 8-bit37 facts · 1 facets
MLX 0.31.2 thread-safety PRs and delivered levels33 facts · 1 facets
mlx 0.32.0 JACCL patch inventory24 facts · 1 facets
MLX 0.32.2 tensor-unit expert-sorted quantized matmul row-limit bug on M52 facts · 1 facets
MLX allocator memory limit GC limit and buffer cache26 facts · 2 facets
MLX and mlx-lm on Apple silicon83 facts · 2 facets
MLX batched decode scheduler crashes7 facts · 1 facets
MLX buffer pool reuse window and cache sizing (mlx issue 3886)8 facts · 1 facets
MLX command-buffer error capture and event poisoning in 0.32.037 facts · 1 facets
MLX command-buffer error propagation PR 374245 facts · 2 facets
MLX discussion 2990 five-node M3 Ultra RDMA benchmark thread17 facts · 1 facets
mlx distributed error propagation via event poisoning (PR 3523, 3742)38 facts · 1 facets
MLX expert parallelism all_to_all PR 315811 facts · 1 facets
MLX gemv_wide bf16 fp16 few-row matmul kernel PR 388832 facts · 1 facets
mlx gemv_wide bf16 small-M kernel in mlx 0.32.11 facts · 1 facets
MLX get_qmv_batch_limit per-generation tuning table18 facts · 1 facets
MLX Metal queue contention between two processes on one GPU3 facts · 1 facets
MLX mixed fp16 and bf16 type promotion in arithmetic12 facts · 1 facets
MLX NAX kernel gating and quantized matmul34 facts · 1 facets
MLX new_thread_unsafe_stream API and Swift concurrency use9 facts · 1 facets
MLX PR 4552 Metal fence deadlock fix in 0.32.3 (MLX_METAL_FAST_SYNCH)39 facts · 2 facets
MLX Python scalar weak typing with half-precision arrays26 facts · 1 facets
MLX qmm_splitk small-M split-K quantized matmul29 facts · 1 facets
MLX qmv_wide kernel PR 3764 and affine gen-15+ gating52 facts · 1 facets
MLX quantized_matmul small-M verify kernels84 facts · 2 facets
MLX thread-local streams and cross-thread lazy array evaluation crashes14 facts · 1 facets
MLX ThreadLocalStream per-thread resolution and cross-thread synchronize no-op1 facts · 1 facets
MLX vs llama.cpp decode and prefill by model size and context86 facts · 2 facets
MLX-LM adapter checkpoints fusion and export9 facts · 5 facets
MLX-LM API and adapter contracts in external post-training integrations33 facts · 6 facets
MLX-LM custom sampling and logits processors16 facts · 3 facets
MLX-LM distillation loss kernels and custom training loss15 facts · 3 facets
MLX-LM distributed fine-tuning and gradient synchronization15 facts · 5 facets
MLX-LM DoRA and distributed training extensions27 facts · 5 facets
MLX-LM integration contracts for external GRPO and GSPO training16 facts · 4 facets
MLX-LM integration contracts for external teacher student distillation17 facts · 6 facets
MLX-LM LoRA and QLoRA versus full fine-tuning11 facts · 5 facets
MLX-LM model architecture integration and loader contracts12 facts · 4 facets
MLX-LM model management and Hugging Face cache lifecycle15 facts · 4 facets
MLX-LM native DoRA and quantized adapter mechanics12 facts · 3 facets
MLX-LM native HTTP request streaming and error contracts15 facts · 5 facets
MLX-LM native multimodal generation and request lifecycle46 facts · 6 facets
MLX-LM native request cancellation and generation resource lifecycle19 facts · 4 facets
MLX-LM native service model lifecycle and release contracts55 facts · 8 facets
MLX-LM native vision inputs and image-aware prompt caching14 facts · 5 facets
MLX-LM perplexity and lm-evaluation21 facts · 7 facets
MLX-LM Python generation and streaming contracts16 facts · 3 facets
MLX-LM Python generation sampling and evaluation53 facts · 8 facets
MLX-LM stateful logits processor rollback during speculative decoding13 facts · 3 facets
MLX-LM training and adapter lifecycle57 facts · 6 facets
MLX-LM training configuration optimization and metrics15 facts · 4 facets
MLX-LM training datasets and prompt masking13 facts · 5 facets
MLX-LM training memory and gradient control9 facts · 5 facets
MLX-LM version pinning and current release compatibility delta13 facts · 7 facets
mlx-optiq residency ceiling near 73 percent of RAM25 facts · 1 facets
mlx-swift-lm and MLXFoundationModels adapter82 facts · 2 facets
mlx.launch jaccl backend flags and hostfile coordinator handling10 facts · 1 facets
mlx.launch remote teardown bug (tmp.None pid file)22 facts · 1 facets
MLX_METAL_FAST_SYNCH and JACCL GPU fence_wait deadlock57 facts · 2 facets
MLX_METAL_FAST_SYNCH effect on event synchronization hangs13 facts · 1 facets
MLX_METAL_GPU_ARCH architecture override as NAX kill switch44 facts · 1 facets
MLXGuidedGeneration and XGrammar constrained decoding on Apple Silicon15 facts · 1 facets
mmap mlock and no-mmap on Apple silicon74 facts · 2 facets
mmproj versioning and mismatch errors for multimodal GGUFs15 facts · 1 facets
Mode collapse and typicality bias in preference tuning5 facts · 3 facets
Model selection by Mac RAM tier103 facts · 2 facets
Model-free 8-10 KiB all_sum loop on 2 and 4 JACCL nodes19 facts · 1 facets
MoE active-parameter decode on unified memory93 facts · 1 facets
MoE expert coverage in imatrix calibration32 facts · 1 facets
MoE expert offload to SSD on macOS82 facts · 1 facets
MoE expert SSD streaming and page-cache residency44 facts · 2 facets
MoE GatherQMM small-M verify cost35 facts · 1 facets
MoE router and shared-expert precision protection in quant recipes29 facts · 1 facets
MoE-PHDS post-hoc declared sparsity fine-tune25 facts · 1 facets
MoESD analysis of MoE speculative decoding batch-size regimes31 facts · 1 facets
MongoDB 8.1–9.0 query-engine changes and AI-assisted optimization143 facts · 9 facets
MongoDB counts, distinct, cursors and read-path tuning947 facts · 9 facets
MongoDB explain output and plan stages571 facts · 9 facets
MongoDB query operators, index bounds and projection878 facts · 9 facets
MongoDB query planner, plan cache, query settings and hints427 facts · 9 facets
MongoDB query shapes, $queryStats, profiler and index usage560 facts · 9 facets
MongoDB sharded query targeting and scatter-gather361 facts · 9 facets
MongoDB sort and pagination optimization241 facts · 8 facets
MongoDB time-series indexes and metaField design719 facts · 9 facets
MongoDB time-series query execution: bucket unpacking, pushdown, block processing and sorts249 facts · 9 facets
MongoDB time-series working-set sizing and sharding52 facts · 8 facets
MTLResidencySet requestResidency postponement under cross-app pressure2 facts · 1 facets
mtmd mergeable bitmaps and temporal frame merging for Qwen-VL video5 facts · 1 facets
mtmd_tokenize_from_parts per-segment tokenization for marked input10 facts · 1 facets
MTP head norm-convention and double-shifted trunk detection54 facts · 1 facets
MTPLX compiled verifier (GraphBank) windows and eager fallback by context length38 facts · 1 facets
MTPLX flash-decoding verify attention kernel (sdpa_nax_flash)35 facts · 1 facets
MTPLX Forge and MTP-preserving MLX conversion20 facts · 1 facets
MTPLX memory guard and request pricing on 8-128 GB Macs49 facts · 1 facets
MTPLX MTP self-drafting Mac server37 facts · 1 facets
MTPLX SSD session cache and SessionBank warm-prefix reuse42 facts · 1 facets
MTPLX Sustained versus Turbo presets and which use compiled verify19 facts · 2 facets
Multi-Agent Orchestration Topologies2 facts · 1 facets
Multi-model serving and memory budgeting in vllm-mlx and oMLX registries17 facts · 1 facets
Multi-model serving on a large Mac with llama-swap110 facts · 2 facets
Multi-root skill discovery and duplicated skill directories13 facts · 1 facets
Multimodal & Vision-Language Model Architecture118 facts · 20 facets
N-gram and prompt-lookup self-speculation for coding agents29 facts · 1 facets
n8n and workflow automation with Ollama94 facts · 9 facets
NAX-aware qmm_splitk for small-M quantized matmul on M540 facts · 1 facets
NLWeb and MCP as agentic-discovery alternatives to llms.txt76 facts · 11 facets
Non-canonical tokenization robustness of instruction-tuned models18 facts · 1 facets
NVIDIA GSP and FSP firmware boot diagnostics on Blackwell under the open kernel modules116 facts · 12 facets
NVIDIA open kernel module on a Thunderbolt eGPU: Xid 79, driver blocking and power management114 facts · 16 facets
Ollama 0.40 MLX-by-default rollout and opt-out39 facts · 1 facets
Ollama alternatives and model sourcing478 facts · 10 facets
Ollama Anthropic adapter tool_use block fidelity19 facts · 1 facets
Ollama client libraries: ollama-python / ollama-js / Go api package83 facts · 7 facets
Ollama cloud models and cloud API: signin / OLLAMA_API_KEY / usage and balance88 facts · 7 facets
Ollama core platform896 facts · 10 facets
Ollama count_tokens 404 stall with Claude Code10 facts · 2 facets
Ollama CPU/GPU split diagnosis and env-var tuning113 facts · 6 facets
ollama create from safetensors with MLX quantization1 facts · 1 facets
Ollama default 262144 context and num_ctx memory cost on Mac8 facts · 1 facets
Ollama deployment and operations502 facts · 11 facets
Ollama deployment, cloud, security and operations500 facts · 11 facets
Ollama desktop app: settings / network exposure / model dir53 facts · 5 facets
Ollama DFlash block-diffusion draft model in mlxrunner21 facts · 1 facets
Ollama embeddings API and local RAG pipelines42 facts · 6 facets
Ollama engine architecture87 facts · 8 facets
Ollama engine architecture: native Ollama engine versus llama.cpp runner and model compatibility16 facts · 4 facets
Ollama engine vs llama engine loader split and mmap support17 facts · 1 facets
Ollama flash attention and KV cache type settings149 facts · 8 facets
Ollama GGUF import renderer detection (qwen3.8 renderer selection)11 facts · 1 facets
Ollama GPU backends and hardware support: CUDA / ROCm / Vulkan / device selection env vars98 facts · 9 facets
Ollama hardware sizing: RAM and VRAM requirements by model and quant92 facts · 8 facets
Ollama importing models: GGUF and safetensors and quantize on create193 facts · 9 facets
Ollama in Docker and Kubernetes96 facts · 9 facets
Ollama installation and service ops on Linux and Windows51 facts · 7 facets
Ollama integrations and ecosystem693 facts · 10 facets
Ollama KV rotation port (OLLAMA_KV_ROTATE)8 facts · 1 facets
ollama launch and coding-agent integrations: Claude Code / Codex / OpenCode / Copilot CLI160 facts · 8 facets
Ollama launcher flag set passed to llama-server34 facts · 1 facets
Ollama llama/compat patch layer for llama.cpp43 facts · 1 facets
Ollama MCP: MCP clients and servers on local models131 facts · 8 facets
Ollama memory estimation and multi-GPU placement: SCHED_SPREAD / layer offload fit60 facts · 9 facets
Ollama MLX backend and NVFP4 on Apple silicon70 facts · 1 facets
Ollama mlxrunner speculative depth controller (committed tokens per second)14 facts · 1 facets
Ollama model quantization tags and library variants139 facts · 8 facets
Ollama model registry and library tags and on-disk blob and manifest storage58 facts · 8 facets
Ollama Modelfile authoring: FROM and PARAMETER and TEMPLATE and SYSTEM and ADAPTER and MESSAGE and LICENSE139 facts · 8 facets
Ollama Modelfile RENDERER and PARSER directives and the renderer/parser registri17 facts · 1 facets
Ollama Modelfile TEMPLATE authoring in Go templates for chat and tool-calling models17 facts · 7 facets
Ollama multimodal projector offload disable policy37 facts · 1 facets
Ollama native tool-call parser extraction for Qwen function XML35 facts · 2 facets
Ollama observability: logs / /api/ps / metrics / tracing46 facts · 6 facets
Ollama on macOS61 facts · 1 facets
Ollama OpenAI and Anthropic compatibility endpoints73 facts · 7 facets
Ollama Qwen3.8 reasoning-effort instructions injected into the system turn25 facts · 1 facets
Ollama qwen3_5 MTP loader and SelfDraft path41 facts · 1 facets
Ollama REST API: generate and chat with streaming NDJSON and errors and usage98 facts · 9 facets
Ollama runner no-mmap default on Metal and use_mmap option22 facts · 1 facets
Ollama security hardening: auth proxies / exposure / CVEs51 facts · 8 facets
Ollama server operations686 facts · 9 facets
Ollama server ops, scheduling, GPU, sizing and desktop683 facts · 9 facets
Ollama server scheduling: NUM_PARALLEL / MAX_LOADED_MODELS / MAX_QUEUE / keep_alive eviction141 facts · 8 facets
Ollama structured outputs on thinking models5 facts · 1 facets
Ollama templates and scale-out112 facts · 12 facets
Ollama thinking capability and reasoning controls147 facts · 10 facets
Ollama usesOllamaRenderedChat versus native llama-server Jinja chat path16 facts · 1 facets
Ollama vision and multimodal usage13 facts · 3 facets
Ollama VRAM-tiered default num_ctx and v1 num_ctx dropping1 facts · 1 facets
Ollama web search and web fetch API66 facts · 6 facets
oMLX /health liveness versus scheduler wedge8 facts · 1 facets
oMLX and Rapid-MLX runtimes120 facts · 1 facets
oMLX boundary snapshot store serialization and async cache-store worker locking45 facts · 1 facets
oMLX custom quantization loader dispatcher (maybe_load_custom_quantization)43 facts · 1 facets
oMLX engine serialization A/B (OMLX_SERIALIZE_ENGINE_GPU) results13 facts · 1 facets
oMLX fatal teardown watchdog and wired memory stranding (issues 2334 and 2184)16 facts · 1 facets
oMLX GDN sidecar and rotating-window snapshot size15 facts · 1 facets
oMLX hybrid GDN boundary snapshot capture regression9 facts · 1 facets
oMLX issue 2330: scheduler never dispatches after two identical cached prefills44 facts · 1 facets
oMLX issue 2624: engine stops dispatching for 6 hours with every thread idle33 facts · 1 facets
oMLX memory guard tiers and prefill ceiling on 16-24 GB Macs24 facts · 2 facets
oMLX Metal cache clears wait for the owning stream (PRs 2412 and 2413)15 facts · 1 facets
oMLX multi-engine GPU serialization and cross-engine Metal queue contention24 facts · 1 facets
oMLX OMLX_DISABLE_PRESSURE_RECLAIM and request_pressure_reclaim scheduler path12 facts · 1 facets
oMLX paged SSD cache auto limit policy21 facts · 1 facets
oMLX per-model chat template kwargs and cache-key construction32 facts · 1 facets
oMLX per-model SSD cache isolation quotas and stale-block eviction82 facts · 2 facets
oMLX ProcessMemoryEnforcer pressure levels and adjust_store_cache_cap16 facts · 2 facets
oMLX remaining ad-hoc mx.clear_cache sites needing stream analysis12 facts · 2 facets
oMLX shared MLX executor thread versus per-engine streams14 facts · 1 facets
oMLX store-cache admission gate and 60 s admission stall error12 facts · 1 facets
oMLX trailing partial block and restore-latency limits16 facts · 2 facets
oMLX VLM versus text engine selection and per-model settings17 facts · 1 facets
On-Device & Local LLM Runtimes104 facts · 20 facets
Open-weight model catalogs: Ollama library versus Hugging Face Hub169 facts · 10 facets
Open-weight model licenses and Ollama library terms31 facts · 8 facets
OpenAI gpt-oss compatibility test script for verifying server implementations12 facts · 1 facets
OpenCode compaction config for local providers25 facts · 2 facets
Orion ANE constraint catalog and direct-ANE programming35 facts · 1 facets
Orion direct-ANE runtime via private ANEClient35 facts · 1 facets
Osaurus inference scheduler, model leases and single-residency handoff51 facts · 1 facets
osaurus vmlx-swift-lm runtime and vmlxctl42 facts · 1 facets
ParoQuant pairwise-rotation quantization for MLX50 facts · 1 facets
Parse-then-render byte round-trip tests for reasoning turns29 facts · 1 facets
PCI hotplug resource assignment: hpmmiosize, realloc and BAR placement120 facts · 19 facets
PCIe link training, speed and width on a Thunderbolt eGPU72 facts · 12 facets
PCIe power management and error handling for a Thunderbolt eGPU: ASPM, D3cold, runtime PM, AER and DPC118 facts · 12 facets
Per-collective all_sum latency in decode over JACCL RDMA11 facts · 2 facets
per-expert coverage and per-expert KLD attribution for MoE quants33 facts · 1 facets
Per-model memory measurement with footprint and IOAccelerator18 facts · 1 facets
Per-token collective count times per-call latency model22 facts · 1 facets
Pipeline parallel backpropagation on Apple silicon with mlx-train16 facts · 4 facets
Plaud MCP Integration33 facts · 12 facets
Post-training effects on LLM vocabulary7 facts · 4 facets
Power, PSU and thermals for a Thunderbolt eGPU91 facts · 13 facets
Pre-M5 vs M5 Apple GPU decode behavior for compressed KV2 facts · 1 facets
Prefill-parity gating of prefill tokens-per-second in cross-runtime reports1 facts · 1 facets
Prefix-cache-safe handling of non-leading system turns40 facts · 1 facets
Prefix-stability regression testing of chat templates34 facts · 2 facets
Pretraining versus alignment attribution of lexical tics5 facts · 2 facets
Prism ML ternary Hadamard-rotated weights kernel on Metal14 facts · 1 facets
Prompt cache survival across model unload swap and server restart86 facts · 1 facets
Prompt caching176 facts · 11 facets
Prompt Helper and Optimizer119 facts · 18 facets
Prompt Lookup49 facts · 11 facets
Prompt processing versus decode on Apple GPUs and Neural Accelerators66 facts · 1 facets
Prompt-cache invalidation by agent clients121 facts · 2 facets
Prompt-format mirroring and structural priming in output6 facts · 3 facets
Prompt-token counting parity across runtimes34 facts · 1 facets
Q4_K_M dequantization cost vs MLX affine g64 on dense decode25 facts · 1 facets
Q4_K_M vs Q4_K_S decode on MoE (Q6_K ffn_down_exps share)16 facts · 1 facets
Q6_K Metal mat-vec cost inside Q4_K_M files32 facts · 1 facets
QJL residual correction needed or harmful1 facts · 1 facets
Quantization formats for Apple silicon (GGUF vs MLX)73 facts · 2 facets
Qwen 3.6 27B GGUF quality benchmark per-quant KL (localbench, 87 quants)16 facts · 1 facets
Qwen 3.8 chat-template fixes and reasoning-level mapping46 facts · 1 facets
Qwen chat template whitespace normalisation of tool-call and think blocks30 facts · 1 facets
Qwen3.5-27B dense Unsloth KLD table for dense versus MoE elasticity14 facts · 2 facets
Qwen3.6 preserve_thinking chat-template flag and prompt-cache reuse78 facts · 1 facets
RamaLama and the Ollama registry156 facts · 11 facets
RamaLama: container-native model runner using the Ollama registry21 facts · 5 facets
Rapid-MLX server and kv-disk-checkpoint-interval19 facts · 2 facets
Rapid-MLX shutdown-time disk save14 facts · 1 facets
Really Simple Licensing (RSL)157 facts · 8 facets
Reasoning field naming across servers12 facts · 1 facets
Reasoning Models and Test-Time Compute135 facts · 25 facets
Reasoning-block trailing newline parser bug causing agent loops12 facts · 1 facets
Reasoning-parser versus tool-parser interaction134 facts · 2 facets
Reasoning-token cache invalidation across turns28 facts · 1 facets
Reference self-flip floor from cache_prompt and batch-size nondeterminism19 facts · 1 facets
Reproducible eGPU bring-up and configuration drift detection108 facts · 19 facets
Resident-model standing power overhead on unified memory (about 21 W)21 facts · 1 facets
Responses API client-executed tool_search support in local servers10 facts · 1 facets
Revision-bound embedding index migration18 facts · 4 facets
Rewriting llama-server overflow errors to Claude Code's recognised wording25 facts · 1 facets
RLHF & RL Training Infrastructure114 facts · 22 facets
robots.txt and the Content-Signal AI-preference extension107 facts · 10 facets
Routed-expert ownership split under ds4 streaming TP31 facts · 1 facets
router --models-max swap ordering (unload before load) peak memory34 facts · 2 facets
Router session keying when subagents reuse metadata.user_id1 facts · 1 facets
router top-k agreement under quantization as a diagnostic33 facts · 1 facets
Running LLM models locally on a Mac34 facts · 3 facets
rustane warm-page-cache pread fanout (ncdrone/rustane)11 facts · 1 facets
Scaling Ollama across replicas: load balancing and when to move to vLLM16 facts · 6 facets
Semantic vs Lexical Deduplication for Text Distillation69 facts · 17 facets
Sequential read throughput of expert-sized reads by Apple SSD configuration1 facts · 1 facets
Server-side prefix cache behavior under rolling-window transcripts30 facts · 1 facets
Service accounts and API-key hardening for LAN-exposed local LLM servers29 facts · 1 facets
Silent wrong-output loading of Hadamard-rotated F16 GGUF in stock llama.cpp7 facts · 1 facets
Silent-corruption testing for distributed collectives with rank-distinct data8 facts · 1 facets
size-matched KLD reporting for local quants35 facts · 1 facets
Skill Lookup63 facts · 14 facets
Small-message JACCL all_sum latency microbenchmark protocol11 facts · 1 facets
Sparse V attention-gated dequant1 facts · 1 facets
Speculative decoding and MTP on Apple silicon142 facts · 2 facets
Speculative decoding verify batches to amortize ANE dispatch34 facts · 1 facets
Speculative decoding with ANE-resident drafter32 facts · 1 facets
Speculative decoding with structured-output grammar at reasoning boundaries26 facts · 1 facets
SqueezeBits Yetter disaggregated ANE-prefill GPU-decode engine1 facts · 1 facets
SSD bandwidth growth per Apple chip generation and 397B projection31 facts · 2 facets
SSD endurance and wear under local LLM inference39 facts · 1 facets
SSD expert streaming and cluster sharding for MoE on Mac38 facts · 1 facets
SSD write budgets and wear for KV session stores26 facts · 1 facets
Static link-local IPv4 per Thunderbolt port for JACCL meshes23 facts · 1 facets
stillwarm llama-server KV persistence wrapper34 facts · 1 facets
Structured Output Constraints and LLM Hallucination Mitigation49 facts · 21 facets
Supervisor-side liveness probes for llama-server (completion probe plus SIGKILL)3 facts · 1 facets
Suspend, resume and sleep states with a Thunderbolt NVIDIA eGPU on Linux84 facts · 14 facets
Sustained-load thermal throttling ANE versus GPU decode33 facts · 1 facets
Tail-risk quant metrics 99.9% KLD max KLD top-1 agreement28 facts · 1 facets
Target-side deferred commit for recurrent state (SGLang DFlash worker)36 facts · 1 facets
Task-stratified retrieval evaluation21 facts · 4 facets
Task-success versus tool count and prompt size for small local models6 facts · 1 facets
task_info TASK_VM_INFO resident_size versus phys_footprint accounting2 facts · 1 facets
Tensor vs pipeline vs expert parallelism for MoE in mlx-lm97 facts · 1 facets
Tensor-parallel all-reduce count per transformer layer in MLX shard_linear31 facts · 1 facets
Ternary Bonsai 2 27B on MTPLX with grafted Qwen3.8 draft head18 facts · 1 facets
Ternary GGUF packings PTQ1_0 and PQ2_0 in the Prism llama.cpp fork14 facts · 1 facets
Text Canonicalization for Exact-Match Deduplication Prep46 facts · 10 facets
Thermal, power and battery behavior during local inference68 facts · 1 facets
Throughput cliff versus vm_stat decompressions on 24 GB M42 facts · 1 facets
Thunderbolt 5, Barlow Ridge and OCuLink eGPU topologies on Linux65 facts · 12 facets
Thunderbolt boot-device authorization and NVIDIA CDI for an eGPU on Linux59 facts · 9 facets
Thunderbolt Bridge bridge0 and STP fixes for RDMA mesh setup12 facts · 2 facets
Thunderbolt eGPU on Linux for local LLM inference55 facts · 8 facets
Thunderbolt firmware updates and kernel-regression hygiene for a Linux eGPU94 facts · 14 facets
Time-to-first-token measurement artifacts34 facts · 1 facets
Token-level generation-versus-render drift measurement harness35 facts · 1 facets
Tool-call parser and chat-template mismatch179 facts · 2 facets
Tool-call repair proxies and self-healing parsers24 facts · 2 facets
Tool-calling benchmarks for local models25 facts · 1 facets
TQ4_1S Hadamard-rotated weight quantization in llama.cpp fork43 facts · 1 facets
Training an MTP adapter for a model with no native head33 facts · 2 facets
Transformer Architecture Internals & Variants125 facts · 19 facets
Tree attention verification on hybrid recurrent targets35 facts · 1 facets
TriAxialKV per-role mixed-precision KV quantization for agentic prefills11 facts · 1 facets
TurboQuant and rotation-based KV quantization on Metal116 facts · 1 facets
TurboQuant Hadamard-rotation codebook weight quantization32 facts · 1 facets
TurboQuant KV cache compression (Hadamard, Lloyd-Max, QJL)1 facts · 1 facets
Two exo models sharing one Mac GPU under fast synch23 facts · 1 facets
Two llama.cpp or llama-swap models loaded concurrently on one GPU: stability4 facts · 1 facets
UC queue pair one-direction drop warm-up check25 facts · 1 facets
UD-IQ4_NL_XL and legacy Q4_NL Q5_1 types on Metal kernels33 facts · 1 facets
UltraFusion die-to-die latency and irregular MoE access4 facts · 1 facets
Unattended remote recovery and out-of-band access for a Thunderbolt eGPU host110 facts · 17 facets
Uninterruptible Us+ rank processes in the Thunderbolt RDMA driver7 facts · 1 facets
Unsloth Desktop Studio macOS app running GGUF and MLX62 facts · 1 facets
Unsloth Dynamic GGUF methodology58 facts · 2 facets
Unsloth server-side tools versus agent passthrough11 facts · 1 facets
Unsloth Studio as an Anthropic-compatible endpoint for Claude Code16 facts · 1 facets
Upstreaming Prism ternary types 142/143 into llama.cpp and Ollama16 facts · 1 facets
Vector LUT and mixed 2/4-bit GPTQ quantization for ANE43 facts · 1 facets
Verifying a vocabulary fix with before-and-after tic rates6 facts · 2 facets
Vision-Language Model (VLM) Layout Parsing and Document Zoning40 facts · 11 facets
vLLM parser engine grammar (vllm/parser) and structural-tag strict tool calling29 facts · 1 facets
vLLM XML tool_call emitted inside think block loses tool calls35 facts · 2 facets
vLLM-Metal hybrid KV cache manager and prefix caching16 facts · 2 facets
Voice and Real-Time Agent Design138 facts · 20 facets
Wall-power meter calibration of SoC-rail energy estimates26 facts · 1 facets
Weight Quantization Footprints2 facts · 1 facets
Why LLMs converge on the same words: mode collapse and post-training lexical effects28 facts · 6 facets
WindowServer GPU contention and display-sleep mitigation16 facts · 1 facets
XGrammar structural tags for Gemma 4 and Harmony tool calls16 facts · 1 facets
XNU vm_per_task_user_wire_limit and global wire sysctl defaults on Apple silicon32 facts · 1 facets
Zipfian hot-row cache tier for n-gram tables (DRAM over NVMe)14 facts · 1 facets
MongoDB Expert Knowledge588 concepts
$_internalUnpackBucket explain reading9 facts · 4 facets
$bucket-bucketAuto3 facts · 1 facets
$dateTrunc Downsampling124 facts · 6 facets
$densify-$fill256 facts · 6 facets
$elemMatch semantics on arrays of subdocuments9 facts · 3 facets
$emit Operators156 facts · 7 facets
$exists query bounds on indexes6 facts · 4 facets
$facet110 facts · 6 facets
$function and server-side JavaScript hardening16 facts · 5 facets
$geoIntersects139 facts · 7 facets
$geoNear Aggregation Stage159 facts · 6 facets
$geoWithin and $centerSphere178 facts · 7 facets
$graphLookup123 facts · 7 facets
$group accumulator memory caps8 facts · 4 facets
$groupByDistinct internal stage13 facts · 5 facets
$lookup228 facts · 6 facets
$merge and $out Materialized Views176 facts · 8 facets
$mergeCursors stage in explain10 facts · 4 facets
$near and $nearSphere138 facts · 6 facets
$search Operators156 facts · 6 facets
$setWindowFields115 facts · 7 facets
$setWindowFields Window Functions217 facts · 7 facets
$source Operators127 facts · 5 facets
$top/$bottom accumulators rewrite6 facts · 3 facets
$unionWith101 facts · 6 facets
2d Indexes41 facts · 7 facets
2dsphere Indexes58 facts · 7 facets
5.6.x RawBsonDocument codec regression60 facts · 6 facets
5.7/5.8 release notes62 facts · 6 facets
8.0.x regression catalog50 facts · 7 facets
Access Control41 facts · 5 facets
Adaptive Timeouts in Database Drivers18 facts · 4 facets
Admin API alert configurations for billing events11 facts · 3 facets
afterClusterTime18 facts · 4 facets
Aggregation Expressions72 facts · 7 facets
Aggregation Pipeline in Charts66 facts · 6 facets
Air-Gap and Local Mode78 facts · 7 facets
AKO CRDs68 facts · 5 facets
AKO Dry Run Mode11 facts · 4 facets
AKO GitOps62 facts · 6 facets
AKO Helm Installation72 facts · 7 facets
AKO Independent CRDs62 facts · 7 facets
AKO Reconciliation Skip Annotation67 facts · 4 facets
AKO Subobject CRDs Deprecated51 facts · 6 facets
AKO Troubleshooting59 facts · 5 facets
AKO vs Terraform86 facts · 6 facets
AKO Workload Identity69 facts · 6 facets
AKS Atlas Kubernetes Operator94 facts · 6 facets
AKS Workload Identity Atlas69 facts · 5 facets
Analytics Node Configuration63 facts · 6 facets
Analytics Node Cost Model62 facts · 6 facets
Analytics Node Monitoring52 facts · 6 facets
Analytics Node Read Preference Routing60 facts · 6 facets
Analytics Node Sizing57 facts · 5 facets
Analytics node tier prorating10 facts · 4 facets
AND_SORTED vs AND_HASH plan stages12 facts · 4 facets
Anti-Patterns11 facts · 4 facets
App Services Authentication Providers123 facts · 7 facets
App Services Billing Model73 facts · 6 facets
App Services CLI Deployment74 facts · 6 facets
App Services Context55 facts · 6 facets
App Services Migration Paths4 facts · 3 facets
App Services Schema Validation3 facts · 2 facets
App Services Values and Secrets7 facts · 3 facets
Archive Data Expiration Rule17 facts · 3 facets
Archive Schedule Window15 facts · 3 facets
ASP Pricing Model52 facts · 6 facets
Atlas Access Control and RBAC13 facts · 3 facets
Atlas Activity Feed17 facts · 4 facets
Atlas Admin API GCP Auth11 facts · 3 facets
Atlas Admin API invoice endpoints24 facts · 4 facets
Atlas AI Services Pricing (Agent Engine and Voyage AI)85 facts · 10 facets
Atlas Azure Regions Mapping16 facts · 5 facets
Atlas Bicep Private Endpoint14 facts · 4 facets
Atlas Billing and Invoice Anatomy93 facts · 8 facets
Atlas Billing Mechanics and Cost Visibility77 facts · 8 facets
Atlas Charts billing dashboards15 facts · 2 facets
Atlas CLI Architecture Internals42 facts · 4 facets
Atlas CLI Benchmark Metrics42 facts · 4 facets
Atlas CLI Failure Scenarios51 facts · 4 facets
Atlas CLI Integration45 facts · 6 facets
Atlas CLI Operational Runbook52 facts · 3 facets
Atlas CLI Scripting19 facts · 6 facets
Atlas CLI Terraform Plugin16 facts · 4 facets
Atlas Cloud Backup (snapshots)15 facts · 3 facets
Atlas Cluster IaC22 facts · 6 facets
Atlas Cluster Topology and Tier Economics80 facts · 7 facets
Atlas Compliance Certifications13 facts · 2 facets
Atlas Cost Commitments, Cross-Org Billing and FinOps Tooling56 facts · 7 facets
Atlas Cost Explorer and Billing Data API94 facts · 10 facets
Atlas Credits Prepaid Subscriptions and Overage67 facts · 9 facets
Atlas Data API (EOL)16 facts · 4 facets
Atlas Data API Removal48 facts · 15 facets
Atlas Data Federation GCS14 facts · 3 facets
Atlas Diagnostics Expert92 facts · 19 facets
Atlas Envelope Encryption GCP18 facts · 4 facets
Atlas Federated Authentication99 facts · 20 facets
Atlas federated database users and groups40 facts · 4 facets
Atlas Flex Pricing and Flex-vs-Dedicated Break-Even77 facts · 11 facets
Atlas Gen2 ARM hardware24 facts · 6 facets
Atlas GraphQL API (EOL)11 facts · 4 facets
Atlas GraphQL API Removal12 facts · 5 facets
Atlas Hybrid Fusion and BM25 Diagnostics19 facts · 7 facets
Atlas IAM Compliance Mapping20 facts · 4 facets
Atlas Identity Federation and Resource Policy Boundaries42 facts · 5 facets
Atlas IP access list for service accounts22 facts · 3 facets
Atlas IP Access List Ownership Conflict14 facts · 4 facets
atlas kubernetes config generate15 facts · 4 facets
Atlas Kubernetes Operator49 facts · 15 facets
Atlas Kubernetes Operator AKO v2.1420 facts · 3 facets
Atlas LDAP Azure AD DS23 facts · 5 facets
Atlas LDAPS (Deprecated 8.0)21 facts · 4 facets
Atlas Live Migration8 facts · 4 facets
Atlas Log Push SIEM18 facts · 5 facets
Atlas MACC Eligibility13 facts · 5 facets
Atlas Maintenance Windows125 facts · 41 facets
Atlas marketplace private offers14 facts · 4 facets
Atlas nonCompliantResources endpoint15 facts · 4 facets
Atlas org mapping and domain mapping48 facts · 6 facets
Atlas Organization Roles16 facts · 5 facets
Atlas Organization Teams16 facts · 3 facets
Atlas Performance Advisor Auto-Index Evaluation60 facts · 5 facets
Atlas Performance Advisor index suggestions12 facts · 3 facets
Atlas Pricing Programs, Cost Governance and TCO43 facts · 7 facets
Atlas Private DNS Zones Azure8 facts · 4 facets
Atlas Programmatic API Keys (Legacy)18 facts · 5 facets
Atlas Query Profiler and Performance Advisor12 facts · 4 facets
Atlas Query Shape Insights10 facts · 6 facets
Atlas Query Targeting alerts12 facts · 6 facets
Atlas Required Memory metric sizing9 facts · 4 facets
Atlas Resource Policies Cedar70 facts · 6 facets
Atlas Search and Dedicated Search Nodes Cost85 facts · 9 facets
Atlas Search Anti-Patterns14 facts · 4 facets
Atlas Search Architecture14 facts · 3 facets
Atlas Search for substring matching11 facts · 5 facets
Atlas Search index sync lag and search-node sizing13 facts · 5 facets
Atlas Search regex and wildcard operator cost7 facts · 3 facets
Atlas Search searchAfter pagination10 facts · 5 facets
Atlas Secretless KV Authentication14 facts · 3 facets
Atlas Slow-Query Log and Performance Advisor Automation744 facts · 9 facets
Atlas SQL Interface MongoSQL64 facts · 19 facets
Atlas SQL Schema Builder21 facts · 5 facets
Atlas Support Plan Pricing51 facts · 9 facets
Atlas tag taxonomy for showback and chargeback18 facts · 5 facets
Atlas Three-Tier Identity Model13 facts · 6 facets
Atlas Vector Search Automated Embedding rate limits11 facts · 2 facets
Atlas WIF built-in vs callback authentication31 facts · 5 facets
AtlasGov Azure Government12 facts · 4 facets
Attribute pattern and wildcardProjection design11 facts · 5 facets
Auto-scaling tier ranges14 facts · 3 facets
Automated Cluster Scaling Decision Matrix48 facts · 6 facets
Autoscaling tier bounds as cost ceiling8 facts · 5 facets
available read concern14 facts · 4 facets
AWS CDK awscdk-resources-mongodbatlas49 facts · 6 facets
AWS CloudFormation Atlas76 facts · 5 facets
AWS CloudFormation Atlas Resources78 facts · 6 facets
AWS IAM Outbound Identity Federation to Atlas67 facts · 7 facets
AWS ISV Accelerate76 facts · 7 facets
AWS Marketplace Atlas74 facts · 7 facets
AWS PrivateLink88 facts · 8 facets
Azure Key Vault RBAC Atlas13 facts · 3 facets
Azure Native MongoDB ANM18 facts · 2 facets
Azure OpenAI Atlas Vector Search13 facts · 2 facets
Azure Private DNS Resolver17 facts · 5 facets
Azure Synapse Atlas Data Federation18 facts · 6 facets
Backup and PITR cost modelling16 facts · 5 facets
Backup Compliance Policy (WORM)54 facts · 6 facets
Backup Cost Optimization14 facts · 5 facets
Backup Daemon19 facts · 5 facets
Backup Daemon and Head DB14 facts · 3 facets
Backup snapshot storage growth cost12 facts · 4 facets
Backup Verification and Tabletop Exercises10 facts · 5 facets
Batch Writes and Idempotency9 facts · 5 facets
BI Connector to MongoSQL Migration28 facts · 5 facets
Billing Alerts and Budget Controls53 facts · 8 facets
BM25 IDF corpus statistics15 facts · 3 facets
BM25 term frequency saturation and field length normalization20 facts · 4 facets
Bounded sort ($_internalBoundedSort)13 facts · 5 facets
Breaking-point / overload testing methodology (first bottleneck vs visible symptom, cascading failure, thundering herd, cache-eviction death spiral)21 facts · 6 facets
BSON BinData vector ingestion14 facts · 4 facets
Bucket-level predicate rewriting for measurement operators8 facts · 5 facets
Burstable M10/M20 tiers12 facts · 5 facets
Bypass SAML mode9 facts · 2 facets
Canary and Shadow-Traffic Comparison12 facts · 5 facets
Capacity Testing11 facts · 2 facets
Causal Consistency109 facts · 39 facets
CDC-patterns48 facts · 14 facets
Cedar forbid-only policy patterns for Atlas19 facts · 6 facets
Cedar policy authoring for cluster size and autoscaling caps14 facts · 5 facets
ceSource cardinality estimation (sampling vs heuristics)10 facts · 4 facets
Change Data Capture Patterns24 facts · 6 facets
Change Point Detection11 facts · 6 facets
Chart Types47 facts · 5 facets
Charts REST API9 facts · 3 facets
Checkpoint Mechanism53 facts · 6 facets
CI Performance Regression Gating12 facts · 4 facets
client sessions17 facts · 3 facets
Client Side Field Level Encryption (CSFLE)17 facts · 6 facets
Client Side Operations Timeout (CSOT)60 facts · 7 facets
Client-side operation timeout (CSOT)23 facts · 6 facets
Cloud Build Atlas API Auth15 facts · 5 facets
Cloud Commit Drawdown via Atlas Marketplace (EDP MACC GCP commit)46 facts · 7 facets
Cloud HSM Atlas14 facts · 2 facets
Cloud Marketplace Billing for Atlas (AWS GCP Azure)53 facts · 7 facets
Cloud Run Atlas Connection Pooling10 facts · 4 facets
Cluster Pause13 facts · 5 facets
Cluster Tier Families and Hourly Pricing (General vs Low-CPU vs NVMe)75 facts · 10 facets
clusterTime19 facts · 3 facets
CMAP Connection Pooling44 facts · 6 facets
Co-located vs dedicated search migration thresholds5 facts · 5 facets
Coefficient of Variation / Run-to-Run Noise Control15 facts · 6 facets
Collation and index sort compatibility6 facts · 3 facets
Collation-based case-insensitive equality12 facts · 3 facets
Common Cost Overruns6 facts · 3 facets
Common Failure Modes21 facts · 4 facets
Common Migration Failures9 facts · 3 facets
Common Sizing Mistakes14 facts · 5 facets
Common upgrade failures11 facts · 4 facets
Compass Anti-Patterns14 facts · 4 facets
Compass CRUD and Documents Tab22 facts · 4 facets
Compass Data Modeling ER Diagrams16 facts · 5 facets
Compass Index Management11 facts · 4 facets
Compass Performance Insights14 facts · 3 facets
Compliance Gaps and Shared Responsibility15 facts · 3 facets
Compound index vs index union for $or10 facts · 5 facets
Connected organizations14 facts · 3 facets
Connection Capacity11 facts · 4 facets
Connection Pool Tuning12 facts · 5 facets
Connection Troubleshooting22 facts · 4 facets
Connector Error Patterns12 facts · 4 facets
Continuous Cloud Backup (PITR)16 facts · 4 facets
Cost Governance Guardrails (Resource Policies and IaC Cost Controls)105 facts · 8 facets
Cost Model1 facts · 1 facets
Cost Monitoring7 facts · 2 facets
COUNT_SCAN covered counts9 facts · 6 facets
Covered queries and projection design15 facts · 5 facets
Crash Stack Trace Symbolization24 facts · 4 facets
Credit expiry and History table8 facts · 1 facets
Cross-Organization Billing and Linked Invoices52 facts · 8 facets
Cross-Region Snapshot Copy13 facts · 4 facets
cross-service causal tokens15 facts · 5 facets
Cross-Vendor Document Database Pricing Comparison (DocumentDB Cosmos DB DynamoDB)119 facts · 11 facets
CSOT Client-Side Operations Timeout13 facts · 3 facets
currentOp planSummary for running operations12 facts · 6 facets
CUSTOM Criteria13 facts · 4 facets
Custom HTTPS Endpoints (EOL)14 facts · 4 facets
Customer Hotfix & Patch Verification9 facts · 4 facets
Cutover Strategies8 facts · 2 facets
Dashboards19 facts · 5 facets
Data Federation over customer S3 with partitioning10 facts · 6 facets
Data Lifecycle Cost Model (TTL vs Online Archive vs Data Federation)90 facts · 10 facets
Data Sources17 facts · 5 facets
Data type selection for storage9 facts · 4 facets
Databricks Workspace Integration15 facts · 5 facets
Datadog Integration18 facts · 3 facets
DATE Criteria39 facts · 6 facets
DATE criteria date format specifications10 facts · 2 facets
DATE criteria field types and formats15 facts · 4 facets
DATE vs CUSTOM criteria selection10 facts · 3 facets
Deadline Propagation and Context Cancellation in MongoDB Drivers40 facts · 3 facets
Deferring Maintenance9 facts · 3 facets
Delbridge Data API13 facts · 5 facets
Disk IOPS Burst Credit Depletion Playbook31 facts · 5 facets
DISTINCT_SCAN for distinct command10 facts · 3 facets
Distributed Sharded Transactions12 facts · 2 facets
DNS and SRV Records28 facts · 5 facets
Domain verification12 facts · 3 facets
Driver compatibility matrix (Java/Node/Python/.NET/Go)11 facts · 2 facets
Driver Examples10 facts · 4 facets
Driver Examples (Node.js, Python, Java)34 facts · 1 facets
Drop-index suggestions endpoint9 facts · 2 facets
dropIndexes abort semantics8 facts · 2 facets
EDP Credits13 facts · 3 facets
Elastic Billing transition8 facts · 5 facets
Elastic Compute Autoscaling2 facts · 2 facets
Embedded Charts26 facts · 6 facets
Embedding SDK7 facts · 1 facets
Emergency Security Patches6 facts · 2 facets
Encryption Requirements (At-Rest, In-Transit, Field-Level)16 facts · 5 facets
Entra ID group overage in Atlas23 facts · 4 facets
Equality-Sort-Range index ordering8 facts · 3 facets
Error Code Hierarchy & Assertion Types14 facts · 4 facets
Error Code Lookup19 facts · 4 facets
Error Codes and Troubleshooting Architecture Internals23 facts · 5 facets
Error Codes and Troubleshooting Benchmark Metrics21 facts · 3 facets
Error Codes and Troubleshooting Failure Scenarios56 facts · 5 facets
Error Codes and Troubleshooting Operational Runbook56 facts · 5 facets
ERS exception for selective range predicates4 facts · 4 facets
EventBridge Integration16 facts · 5 facets
Eviction (clean/dirty targets and triggers)63 facts · 5 facets
expireAfterDays data age calculation9 facts · 4 facets
explain multiKeyPaths interpretation5 facts · 4 facets
Explain verbosity modes10 facts · 4 facets
explain() executionStats reading7 facts · 3 facets
express execution path12 facts · 2 facets
Express MongoDB Driver Pattern49 facts · 5 facets
FastAPI Motor Pattern28 facts · 6 facets
FCV pinning no-downgrade rule20 facts · 4 facets
Feature Compatibility Version (FCV)68 facts · 6 facets
Federated database user mapping by sub/groups claim12 facts · 4 facets
Federation Management Console8 facts · 1 facets
Field-name abbreviation trade-offs15 facts · 7 facets
Find projection vs $project aggregation coverage18 facts · 5 facets
FinOps Framework Applied to Atlas88 facts · 11 facets
FinOps Tooling for Atlas (FOCUS Ingestion Anomaly Detection Budgets)75 facts · 8 facets
Flex backup and recovery planning22 facts · 4 facets
Flex cluster spend ceiling7 facts · 4 facets
Flex Limitations and migration to Dedicated16 facts · 4 facets
Flex Tooling Migration Terraform K8s CLI12 facts · 5 facets
Forcing plans with hint and internal query knobs13 facts · 5 facets
FTDC Chunk Decompression & Stream Parsing37 facts · 7 facets
FTDC Diagnostics59 facts · 6 facets
FTDC Storage Overhead & Retention Budgeting20 facts · 4 facets
Function Context Object19 facts · 4 facets
Fusion score normalization strategies15 facts · 5 facets
GCP Regions Atlas Mapping12 facts · 2 facets
Gen1 vs Gen2 IOPS billing17 facts · 7 facets
Gen1 vs Gen2 storage and IOPS billing12 facts · 4 facets
GKE Atlas Kubernetes Operator11 facts · 4 facets
GKE NodeLocal DNSCache Atlas10 facts · 3 facets
Google Distributed Cloud GDC16 facts · 3 facets
Google Workspace SAML Federation16 facts · 4 facets
Granularity and custom bucketing parameters13 facts · 5 facets
Group-to-role mapping7 facts · 1 facets
Growth Signals13 facts · 3 facets
Hashed vs ranged shard key query trade-offs13 facts · 3 facets
hint in aggregate and update/delete10 facts · 4 facets
History Store (WiredTigerHS.wt)70 facts · 6 facets
HNSW Index Parameters19 facts · 5 facets
Hopping Windows19 facts · 6 facets
HTTPS Endpoints14 facts · 3 facets
Hub-and-Spoke Atlas Networking16 facts · 4 facets
IAM Authentication12 facts · 3 facets
IdP configuration (Entra ID)26 facts · 4 facets
IdP configuration (Okta)12 facts · 4 facets
implicit vs explicit sessions13 facts · 4 facets
Index filters deprecation and migration9 facts · 3 facets
Index hints on time series collections15 facts · 5 facets
Index prefix compression and index size10 facts · 3 facets
Index Storage Cost8 facts · 3 facets
Index Sufficiency Warning5 facts · 3 facets
initial-sync-and-cdc12 facts · 5 facets
Instance Right-Sizing4 facts · 2 facets
JIT user provisioning15 facts · 3 facets
kafka-sink-connector48 facts · 14 facets
kafka-source-connector48 facts · 14 facets
Keyset pagination with compound sort keys7 facts · 5 facets
KMS Encryption at Rest36 facts · 4 facets
Kubernetes Operator Deployment19 facts · 3 facets
Lambda Integration32 facts · 5 facets
Lambda Managed Instances and MongoClient concurrency safety15 facts · 6 facets
Lambda MongoDB Driver Pattern9 facts · 4 facets
Lock-Free Diagnostic Sampling Engine8 facts · 3 facets
M10 shared-vCPU dedicated tier economics15 facts · 5 facets
M30 specs & connection limits16 facts · 5 facets
Maintenance Impact Minimization5 facts · 3 facets
Maintenance Window Configuration17 facts · 3 facets
majority-ack write concern change7 facts · 3 facets
Matryoshka Dimension Truncation for Vector Storage Cost63 facts · 12 facets
maxTimeMS (Server-side Operation Timeout)9 facts · 2 facets
Memory Limits and allowDiskUse21 facts · 5 facets
min()/max() requiring hint7 facts · 2 facets
MongoDB 8.0 WT Improvements (TCMalloc, ExpressPlan)22 facts · 7 facets
MongoDB Advanced Explain: Aggregation, Sharded Plans, Loose Index Scans and the 8.3 Cost-Based Ranker269 facts · 8 facets
MongoDB Aggregation Pipeline65 facts · 24 facets
MongoDB Atlas212 facts · 56 facets
MongoDB Atlas App Services41 facts · 16 facets
MongoDB Atlas AWS Networking57 facts · 14 facets
MongoDB Atlas Charts58 facts · 16 facets
MongoDB Atlas Cost Optimization176 facts · 70 facets
MongoDB Atlas Device SDK99 facts · 29 facets
MongoDB Atlas Flex and Serverless Tiers68 facts · 16 facets
MongoDB Atlas IAM and RBAC74 facts · 18 facets
MongoDB Atlas Infrastructure as Code47 facts · 15 facets
MongoDB Atlas Multi-Cloud65 facts · 19 facets
MongoDB Atlas on Azure64 facts · 23 facets
MongoDB Atlas on GCP84 facts · 24 facets
MongoDB Atlas Online Archive65 facts · 19 facets
MongoDB Atlas Search30 facts · 6 facets
MongoDB Atlas Search and Vector Search34 facts · 12 facets
MongoDB Atlas Stream Processing52 facts · 16 facets
MongoDB Atlas Terraform Provider55 facts · 19 facets
MongoDB Atlas Vector Search46 facts · 15 facets
MongoDB BI Connector and SQL Access64 facts · 19 facets
MongoDB Capacity Planning63 facts · 20 facets
MongoDB Compass240 facts · 84 facets
MongoDB Compliance and Regulatory72 facts · 17 facets
MongoDB Compound Index Design: ESR, Selectivity, Covering and Multikey Bounds675 facts · 9 facets
MongoDB Developer Patterns181 facts · 40 facets
MongoDB Expert Knowledge113 facts · 37 facets
MongoDB Explain Plans, Query Planner and Plan Cache1565 facts · 9 facets
MongoDB Geospatial49 facts · 15 facets
MongoDB Indexes Deep Dive135 facts · 50 facets
MongoDB KB Articles183 facts · 37 facets
MongoDB Major-Version Upgrade Regression Detection8 facts · 3 facets
MongoDB MCP Server read-only and permission model11 facts · 4 facets
MongoDB Migration Patterns66 facts · 19 facets
MongoDB Monitoring and Observability125 facts · 41 facets
MongoDB Multi-Tenancy72 facts · 18 facets
MongoDB Ops Manager and Cloud Manager62 facts · 19 facets
MongoDB Query Optimization Tooling: Compass Explain, Atlas Query Insights and Performance Advisor925 facts · 9 facets
MongoDB Query Shape Optimization: Sort, Pagination, Operators and Sharded Targeting2427 facts · 9 facets
MongoDB Realm Mobile Sync45 facts · 12 facets
MongoDB Replication109 facts · 39 facets
MongoDB Security Architecture69 facts · 16 facets
MongoDB Time-Series Query and Index Optimization1028 facts · 9 facets
MongoDB Transactions72 facts · 20 facets
MongoDB Upgrade Paths215 facts · 52 facets
MongoDB Wildcard and Hidden Indexes, Index Builds and Index Overhead661 facts · 9 facets
mongodb-aggregation-stages-deep220 facts · 63 facets
mongodb-kafka-connector48 facts · 14 facets
mongodb-time-series199 facts · 25 facets
MongoSQL ODBC Driver18 facts · 4 facets
mongosync164 facts · 47 facets
Monitoring Agent17 facts · 4 facets
monotonic reads15 facts · 4 facets
mtools Log Analysis Integration10 facts · 5 facets
Multi-Cloud Replica Sets16 facts · 5 facets
Multi-Document Transactions14 facts · 5 facets
Multi-Environment Terraform Directories vs Workspaces15 facts · 7 facets
Multi-Org Scale Patterns17 facts · 4 facets
Multi-Region and Cross-Cloud Data Transfer Costs52 facts · 9 facets
Multi-region cluster cost premium11 facts · 3 facets
Multi-Region Networking8 facts · 4 facets
Multikey index coverage and multiKeyPaths19 facts · 7 facets
Multikey index sort bounds11 facts · 6 facets
Namespace Insights16 facts · 4 facets
natural hint and collection scans9 facts · 5 facets
Natural language to MongoDB query generation12 facts · 4 facets
Network Access Lists24 facts · 4 facets
Network Connection Quota Management19 facts · 2 facets
Network Egress Costs11 facts · 3 facets
New Relic Integration12 facts · 3 facets
OAuth2 Token Exchange18 facts · 3 facets
Online Archive partition-field selection10 facts · 6 facets
Online Archive query performance optimization10 facts · 5 facets
Online Archive Terraform Resource31 facts · 4 facets
operationTime2 facts · 1 facets
Oplog Sizing16 facts · 5 facets
Oplog windows and Search initial-sync recovery12 facts · 5 facets
Ops Manager Application16 facts · 2 facets
Ops Manager Architecture18 facts · 4 facets
Ops Manager LDAP/Kerberos/SAML/OIDC Federation24 facts · 5 facets
Organization-scoped alert configuration API8 facts · 3 facets
Partial and TTL indexes on time series9 facts · 3 facets
Partial TTL indexes13 facts · 6 facets
Partial unique indexes for soft delete6 facts · 3 facets
Partition fields constraints for DATE rules10 facts · 4 facets
Partition-Based Sync (Legacy)12 facts · 2 facets
Partitioner Strategies10 facts · 5 facets
path-level multikey tracking15 facts · 5 facets
Pause/resume automation with Terraform or GitHub Actions21 facts · 5 facets
Per-query fusion weighting7 facts · 4 facets
Performance Impact4 facts · 1 facets
Performance KB Articles19 facts · 5 facets
Performance Tuning Checklist19 facts · 5 facets
PII Masking & Query Hash Anonymization19 facts · 5 facets
Pipeline Optimization12 facts · 4 facets
Pipeline Stages Reference28 facts · 6 facets
planCacheSize and $planCacheStats8 facts · 4 facets
Planner plan scoring and EOF bonus10 facts · 4 facets
Point of No Return18 facts · 4 facets
Power BI DirectQuery17 facts · 4 facets
Pre-Deployment Cost Estimation and Sizing Model (Atlas Pricing Calculator)96 facts · 11 facets
Private endpoints and VPC peering transfer charges10 facts · 5 facets
Programmatic API Keys Legacy Auth16 facts · 6 facets
Quantile Estimation (DDSketch)7 facts · 4 facets
Query Efficiency as a Cost Lever86 facts · 10 facets
Quick Reference1 facts · 1 facets
RAG Patterns22 facts · 6 facets
RAG Patterns with Vector Search20 facts · 5 facets
Random-key (hashed/UUID) index insert behavior12 facts · 5 facets
Ranked and scored input pipeline eligibility13 facts · 4 facets
Read Concern11 facts · 3 facets
Read Concern Levels110 facts · 39 facets
Read Preference12 facts · 5 facets
Read preference and write routing for cost9 facts · 4 facets
Read vs Write Distribution8 facts · 5 facets
read your own writes21 facts · 4 facets
Read/Write Tickets and Dynamic Concurrency (7.0+)54 facts · 7 facets
Reading slotBasedPlan explain output for time series12 facts · 5 facets
Realm Migration20 facts · 5 facets
Realm Object Model20 facts · 3 facets
Reconciliation and Page Splitting17 facts · 6 facets
Region and Cloud Provider Price Differentials for Atlas85 facts · 9 facets
Relational Migrator11 facts · 2 facets
Replica Set Node Topology Cost75 facts · 10 facets
Replica Set Transactions14 facts · 3 facets
Replica-set election timing65 facts · 6 facets
Replication Lag Monitoring15 facts · 6 facets
Request Hedging23 facts · 7 facets
Reserved Capacity and Committed Use20 facts · 4 facets
Resource Policy Drift Monitoring (nonCompliantResources)30 facts · 7 facets
Resource Tags and Cost Allocation (Showback/Chargeback)136 facts · 11 facets
RESTHeart33 facts · 4 facets
resume-and-checkpoint15 facts · 5 facets
Retryable Transactions21 facts · 4 facets
Retryable Writes63 facts · 6 facets
Right-sizing Atlas tier from cache and CPU metrics7 facts · 4 facets
Right-sizing from Atlas metrics12 facts · 5 facets
Rolling Maintenance Procedure8 facts · 2 facets
rolling upgrade & elections18 facts · 5 facets
Same-field `$or` to `$in` rewrite14 facts · 5 facets
SAML 2.0 SSO flow27 facts · 4 facets
SBE $lookup pushdown and hash join14 facts · 6 facets
SBE vs classic engine defaults20 facts · 3 facets
SBE vs classic plan cache keys9 facts · 4 facets
Scheduled and Predictive Scaling for Atlas Cost134 facts · 12 facets
Schema Design for Storage Cost65 facts · 10 facets
SCIM provisioning34 facts · 5 facets
SDAM Topology State Machine68 facts · 6 facets
Search Highlighting17 facts · 5 facets
Search Index Mapping17 facts · 4 facets
Secret Rotation20 facts · 3 facets
Security Groups13 facts · 4 facets
Security KB Articles16 facts · 4 facets
Self-Managed MongoDB vs Atlas TCO71 facts · 8 facets
SERVER JIRA Ticket Regression Mapping9 facts · 3 facets
Server Selection Algorithm11 facts · 4 facets
Server Selection Timeout7 facts · 4 facets
serverStatus metrics.query.cbr7 facts · 3 facets
Service Account per Environment Pattern15 facts · 4 facets
Service Account Roles22 facts · 3 facets
Service account secret rotation30 facts · 5 facets
Session Windows10 facts · 2 facets
Shard Key Design for Multi-Tenancy14 facts · 4 facets
Shard key selection for query isolation9 facts · 4 facets
Sharded Cluster Cost Economics71 facts · 10 facets
Sharded Cluster Maintenance17 facts · 3 facets
Sharded cluster upgrade ordering63 facts · 6 facets
Sharding Triggers16 facts · 6 facets
SHARDING_FILTER orphan filtering9 facts · 4 facets
Shared-cost allocation rules for managed database services15 facts · 5 facets
Slot-based execution engine eligibility11 facts · 5 facets
Sort direction and compound index prefix rules8 facts · 3 facets
Spark Connector V10 Architecture22 facts · 3 facets
Spark Connector vs Alternatives9 facts · 4 facets
Standard URI Format7 facts · 4 facets
Storage and Data-Lifecycle Cost Levers40 facts · 7 facets
Storage Autoscaling23 facts · 6 facets
Storage Growth and IOPS Forecasting for Cost91 facts · 9 facets
Storage Tier Selection35 facts · 5 facets
Straight-to-8 jump pattern13 facts · 2 facets
Stream Processor Pipeline20 facts · 6 facets
Streaming BSON Parser Architecture22 facts · 5 facets
Streaming Write Semantics9 facts · 3 facets
Support line items per cloud provider on invoices6 facts · 2 facets
Sustained overload / soak testing (memory leaks, connection pool exhaustion, WiredTiger cache thrashing, ticket starvation, oplog window shrinkage)21 facts · 7 facets
Sync Configuration18 facts · 5 facets
Tableau Certified Connector23 facts · 5 facets
Tail Latency Mitigation3 facts · 3 facets
Targeted vs scatter-gather shard routing in explain9 facts · 6 facets
TCMalloc per-CPU caches24 facts · 4 facets
Telemetry Overhead Bounding Algorithms3 facts · 1 facets
Terraform Atlas Provider41 facts · 4 facets
Terraform Integration29 facts · 5 facets
Terraform mongodbatlas_service_account without initial secret8 facts · 3 facets
Terraform Tag Enforcement and Policy-as-Code for Atlas Cost49 facts · 8 facets
Tier 0 Tier 1 Tier 2 Strategy4 facts · 2 facets
Time Series Aggregation22 facts · 7 facets
Time Series Archive Rules34 facts · 4 facets
Timestamp APIs (oldest/stable/pinned)17 facts · 4 facets
TLS Encryption16 facts · 3 facets
tls-x509-auth9 facts · 3 facets
Total count strategies for paginated UIs9 facts · 3 facets
Transaction Anti-Patterns9 facts · 4 facets
Transaction Limits19 facts · 3 facets
transformIdentifiers HMAC privacy mode8 facts · 4 facets
Transit Gateway Patterns18 facts · 6 facets
Trigger and Function Anti-Patterns14 facts · 4 facets
TTL Indexes24 facts · 5 facets
Tumbling Windows16 facts · 6 facets
Unique Indexes22 facts · 5 facets
Unlinking marketplace billing safely13 facts · 3 facets
Upgrade event coverage (pre/during/post)13 facts · 3 facets
Upgrade rollback playbook6 facts · 3 facets
Validating AI-suggested indexes with explain10 facts · 3 facets
Vector Search Quantization and Embedding Storage Cost64 facts · 9 facets
Vertex AI Atlas Vector Search16 facts · 3 facets
VPC Peering45 facts · 4 facets
Wildcard index query-planner behavior and explain rejectedPlans14 facts · 5 facets
Window Functions ($setWindowFields)18 facts · 2 facets
WiredTiger Block and Prefix Compression as Storage Cost Lever83 facts · 10 facets
WiredTiger Storage Engine Internals226 facts · 63 facets
WiredTiger Ticket Metric Telemetry in FTDC35 facts · 7 facets
Workforce and Workload Identity Federation21 facts · 4 facets
Working Set Sizing10 facts · 5 facets
Write Concern17 facts · 4 facets
Software Engineering127 concepts
7-Phase Debugging Workflow46 facts · 6 facets
@vercel/ncc (single-file compilation for CLIs/Actions/Lambda)84 facts · 7 facets
Accessibility for menu bar apps VoiceOver and App Store Accessibility Nutrition Labels9 facts · 3 facets
AI-Native UX and Generative UI Design111 facts · 19 facets
App Privacy nutrition labels age rating export compliance and DSA trader status14 facts · 4 facets
App Review Privacy, AI Consent and Rejection Playbook41 facts · 7 facets
App Review process mechanics Resolution Center appeals and recurring rejection causes for utility and network apps9 facts · 4 facets
App Sandbox network entitlements client and server semantics UDP ICMP and child-process inheritance9 facts · 3 facets
App Store Connect API and CLI automation of submission and review8 facts · 4 facets
Apple Business Manager custom apps and MDM distribution for IT audiences9 facts · 2 facets
Apple Foundation Models on-device diagnosis as an alternative to a cloud AI call10 facts · 5 facets
Apple Platform Frontier for Mac Utilities45 facts · 6 facets
Backend Patterns25 facts · 7 facets
BIS annual self-classification report for exempt mass-market encryption6 facts · 2 facets
BYO API key consent design and Notes for Review template for optional AI and alert features10 facts · 3 facets
Clean-machine QA matrix VM fresh user latest macOS release and physical Mac8 facts · 3 facets
Coding Standards53 facts · 13 facets
Compose Multiplatform Patterns31 facts · 13 facets
CoreWLAN SSID access and Location Services authorization8 facts · 4 facets
CPython Performance Profiling and Acceleration53 facts · 15 facets
CPython Runtime Internals (Free-Threading, Subinterpreters, JIT)47 facts · 15 facets
Crash and log collection for store apps Organizer MetricKit OSLog and log collect versus zero telemetry10 facts · 4 facets
Dark mode semantic colours and SF Symbols in status items6 facts · 3 facets
Debugging Strategies49 facts · 13 facets
Distributed Systems & Consensus (theory + blockchain mechanisms)21 facts · 5 facets
Docs-as-Code & Static-Site Generators2 facts · 1 facets
Document & File Formats18 facts · 5 facets
Document Store Bootstrapper54 facts · 13 facets
Editorial Micro-Typography & Type-Craft Defects221 facts · 63 facets
Encrypted DNS DoH DoT system settings changes in macOS 26-278 facts · 2 facets
Excel and Spreadsheet Automation108 facts · 26 facets
Frontend Design38 facts · 7 facets
Glean Enterprise CLI75 facts · 8 facets
Guideline 2.1 Information Needed reply: review notes8 facts · 3 facets
Guideline 2.3 accurate metadata and 4.2 minimum functionality and hidden-feature strings9 facts · 6 facets
Guideline 2.4.2 power and resource efficiency for polling network monitors7 facts · 3 facets
Guideline 2.5 public APIs and bundled interpreter and private-API string scan (ITMS-90338)7 facts · 3 facets
Guideline 5.1.1 and 5.1.2(i) privacy purpose strings and third-party AI data-sharing consent10 facts · 2 facets
Guideline 5.2 trademark and IP rules in app metadata8 facts · 3 facets
Hardened Runtime Gatekeeper and notarization for a Developer ID twin build12 facts · 4 facets
HIG for menu bar extras windows and notifications and Liquid Glass icons Icon Composer13 facts · 5 facets
Index lifecycle and health404 facts · 9 facets
Index types536 facts · 9 facets
Indexing2000 facts · 11 facets
Interface-bound sockets IP_BOUND_IF and required_interface and sandbox behaviour9 facts · 4 facets
IPv6-only DNS64 NAT64 review network and IPv4-literal probes and Guideline 2.5.5 and Internet Sharing NAT64 testing8 facts · 5 facets
JavaScript Build Tooling and Bundlers49 facts · 13 facets
JavaScript/TypeScript Runtimes (Deno, Bun, Edge) & WinterTC Interop115 facts · 16 facets
Lightweight Markup Languages (reST/AsciiDoc/Org)2 facts · 1 facets
llms.txt & Markdown-for-LLMs2 facts · 1 facets
Local Network privacy TN3179 NSBonjourServices and detecting a denial12 facts · 3 facets
Mac App Store App Review Guidelines for Sandboxed Utilities57 facts · 7 facets
Mac App Store Guideline 2.4.5 sandbox self-contained bundle and no-root rules10 facts · 2 facets
Mac App Store Readiness: Residual Gaps for Sandboxed Monitors53 facts · 7 facets
macOS 27 and 26 platform changes affecting sandboxed menu-bar network apps8 facts · 4 facets
macOS App Sandbox Networking and Entitlements68 facts · 7 facets
macOS App Testing and Release QA76 facts · 6 facets
macOS Menu-Bar App Design62 facts · 8 facets
Markdown2 facts · 1 facets
Markdown Authoring & Spec (CommonMark/GFM)2 facts · 1 facets
Markdown Linting & Quality Gates2 facts · 1 facets
Markdown Processing & ASTs (unified/remark/rehype)2 facts · 1 facets
MDX (Markdown + JSX)2 facts · 1 facets
Menu bar overflow notch hiding and user-disabled menu bar items7 facts · 3 facets
Mobile iOS Design49 facts · 12 facets
mongos as MongoDB's native router & why MongoDB rarely uses third-party proxies16 facts · 4 facets
Network fault injection for testing monitors Network Link Conditioner dummynet pfctl and DNS blackhole11 facts · 3 facets
Network.framework NWPathMonitor and NWConnection versus SCNetworkReachability8 facts · 4 facets
Node.js & TypeScript ORMs and Query Builders101 facts · 17 facets
Node.js Application Security Hardening85 facts · 15 facets
Node.js Async Control-Flow, Errors & Context Propagation78 facts · 16 facets
Node.js Backend Frameworks (Fastify, NestJS, Hono)42 facts · 11 facets
Node.js Build Tooling & Bundlers102 facts · 17 facets
Node.js Built-in Test Runner (node:test deep features)86 facts · 16 facets
Node.js Concurrency Internals119 facts · 30 facets
Node.js HTTP & Networking94 facts · 17 facets
Node.js Modern Batteries-Included Built-ins98 facts · 17 facets
Node.js Module Resolution & ESM/CJS Interop92 facts · 17 facets
Node.js Native Addons (N-API, node-gyp, node-addon-api)2 facts · 1 facets
Node.js Native TypeScript, Permission Model & Single Executable Applications81 facts · 17 facets
Node.js Package Management & Supply-Chain88 facts · 15 facets
Node.js Production Diagnostics & Profiling80 facts · 18 facets
NSStatusItem versus SwiftUI MenuBarExtra and activation policy LSUIElement and Dock tile9 facts · 5 facets
Okta Expert228 facts · 60 facets
ORM index definitions322 facts · 10 facets
Pandoc Document Conversion2 facts · 1 facets
Privacy manifests PrivacyInfo.xcprivacy and required-reason APIs on macOS10 facts · 2 facets
py2app and Python packaging pipeline for the Mac App Store nested signing entitlements and slimming9 facts · 4 facets
Pydantic v2 Data Validation and Modeling102 facts · 19 facets
Python in the Browser & WebAssembly (Pyodide, PyScript, WASI/CPython)60 facts · 16 facets
Python PyObjC rumps py2app as a Mac App Store UI stack limits and native-shell options10 facts · 3 facets
Python Static Type Checking75 facts · 18 facets
Python Supply-Chain & Application Security93 facts · 15 facets
Python Testing with pytest, fixtures, and Hypothesis2 facts · 1 facets
Query planner, explain plans and covered queries245 facts · 11 facets
Repo Bootstrapper104 facts · 25 facets
Repo File Analyzer115 facts · 25 facets
Review-environment reality: reviewer first launch on a clean account network and latest macOS8 facts · 3 facets
Rust Language and Rust for Blockchain35 facts · 9 facets
Sandbox verification harness sandboxed ad-hoc build sandbox-deny logs and container inspection11 facts · 4 facets
SCDynamicStore and NWPathMonitor event-driven change detection replacing fixed-interval probing4 facts · 3 facets
screen recording and resubmission protocol8 facts · 3 facets
Screen recording for App Review capture tools codecs size and attach versus link6 facts · 3 facets
Search and vector indexes246 facts · 11 facets
Slack Developer Platform91 facts · 32 facets
SMAppService login items and privileged helpers for Mac App Store versus Developer ID10 facts · 4 facets
Swift shell with embedded Python helper over XPC in a sandboxed app8 facts · 4 facets
TestFlight for Mac internal and external testing build processing and beta review10 facts · 2 facets
TypeScript Advanced Types79 facts · 28 facets
TypeScript Compiler API99 facts · 23 facets
TypeScript Compiler Configuration117 facts · 18 facets
TypeScript Compiler Performance and tsgo99 facts · 17 facets
TypeScript Declaration Files86 facts · 17 facets
TypeScript Decorators77 facts · 19 facets
TypeScript ESLint Typed Linting81 facts · 18 facets
TypeScript Migration and Adoption98 facts · 17 facets
TypeScript Project References88 facts · 18 facets
UI automation of menu bar apps XCUITest and Accessibility API9 facts · 3 facets
UI/UX Design318 facts · 41 facets
UserNotifications UNUserNotificationCenter migration from NSUserNotification8 facts · 4 facets
uv — The Unified Python Toolchain111 facts · 22 facets
V8 Engine Internals (hidden classes / inline caches, JIT pipeline, Orinoco GC)110 facts · 14 facets
Validate and upload altool Transporter App Store Connect API and ITMS error catalogue11 facts · 4 facets
Web App Testing36 facts · 10 facets
Web Design28 facts · 7 facets
Web Platform and Browser APIs42 facts · 9 facets
Word Document Manipulation83 facts · 24 facets
Writing and Documentation125 concepts
10-minute Getting Started tutorial93 facts · 8 facets
10/20/30 rule (Kawasaki)100 facts · 6 facets
14-pass review methodology32 facts · 7 facets
24-hour cooling-off rule50 facts · 7 facets
750-word discipline42 facts · 7 facets
8-paragraph skeleton35 facts · 6 facets
A/B testing conventions31 facts · 6 facets
Academic and Citation Writing64 facts · 15 facets
Accessibility Writing54 facts · 15 facets
AI Collaboration Writing23 facts · 7 facets
AI-Assisted Copywriting Workflow20 facts · 5 facets
API Documentation Craft53 facts · 14 facets
Audio Script Writing56 facts · 14 facets
Auditing the vocabulary of system prompts and instruction files5 facts · 3 facets
Brand Voice Guide Writing54 facts · 14 facets
Candor and sincerity marker tics5 facts · 3 facets
Case Study Writing47 facts · 11 facets
Changelog and Release Notes110 facts · 19 facets
Changelogs for Humans44 facts · 11 facets
Chatbot Conversation Writing66 facts · 14 facets
Code comment narration and over-explanation5 facts · 4 facets
Code Plan Writing30 facts · 8 facets
Commit message and PR description tells6 facts · 3 facets
Commit Message Craft56 facts · 15 facets
Conceptual metaphor source domains in technical prose7 facts · 1 facets
Consequences for tic lists and detectors6 facts · 3 facets
Context-borne lexical contagion5 facts · 4 facets
Contrastive negation and false-dichotomy framing7 facts · 2 facets
Conversion Copywriting and Voice of Customer17 facts · 5 facets
Cover Letter Writing45 facts · 14 facets
Crisis PR Writing43 facts · 12 facets
Dead versus live metaphors in engineering writing7 facts · 4 facets
Defensive-code and over-engineering signatures6 facts · 5 facets
Diátaxis Explanation Quadrant34 facts · 17 facets
Diátaxis How-To Quadrant41 facts · 22 facets
Diátaxis Reference Quadrant46 facts · 22 facets
Diátaxis Tutorial Quadrant48 facts · 24 facets
Doc Archaeology37 facts · 10 facets
Document Critique128 facts · 20 facets
Draft Review Revise Loop69 facts · 15 facets
Edit protocol for colliding metaphors4 facts · 2 facets
Editing and Revision55 facts · 21 facets
Editorial commentary in neutral prose6 facts · 3 facets
Email Craft59 facts · 17 facets
Engineering-metaphor vocabulary tics in LLM output6 facts · 5 facets
Error Message Craft57 facts · 15 facets
Excess-vocabulary frequency method7 facts · 4 facets
Feedback loop and baseline contamination4 facts · 2 facets
Few-shot exemplars versus banned-word lists for style control7 facts · 4 facets
Founder Letter Writing52 facts · 18 facets
GenAI for Instructional Design & AI Tutors46 facts · 12 facets
Good engineering prose versus a tell7 facts · 4 facets
Headline craft44 facts · 13 facets
Homogenization of professional and scientific prose7 facts · 3 facets
Human adoption of LLM vocabulary and its effect on tic baselines28 facts · 5 facets
Human adoption of LLM vocabulary in speech and writing5 facts · 3 facets
Human baselines and control words for tic detection7 facts · 4 facets
Human Performance Technology & Performance Support134 facts · 32 facets
Instructional Design & Course Architecture143 facts · 26 facets
Job Description Writing51 facts · 14 facets
Learning Measurement & Training Evaluation40 facts · 19 facets
Legal Adjacent Writing54 facts · 14 facets
Literal-referent rewriting protocol5 facts · 3 facets
LLM engineering-metaphor tics: term of art versus reflexive tic28 facts · 6 facets
LLM rhetorical-pattern tells in prose28 facts · 5 facets
LLM tells in code, commit messages, comments and READMEs29 facts · 7 facets
Localization Friendly Writing56 facts · 16 facets
Maintaining a living tic list7 facts · 4 facets
Measuring convergence against pre-LLM baselines6 facts · 4 facets
Measuring LLM lexical tics: excess vocabulary, baselines, drift30 facts · 6 facets
Meeting Minutes and Decision Log48 facts · 16 facets
Metaphor collision as a detection signal3 facts · 2 facets
Microcopy and UI Writing49 facts · 15 facets
Mixed metaphor and catachresis6 facts · 4 facets
Mixed metaphors and catachresis as signs of reflexive figurative language27 facts · 6 facets
MongoDB University & Certification74 facts · 17 facets
Negative-instruction backfire in style prompts7 facts · 5 facets
NPS Response Writing56 facts · 15 facets
Offer Design and Value Proposition82 facts · 18 facets
OKR Writing57 facts · 14 facets
One-Pager Writing65 facts · 15 facets
Op-ed writing75 facts · 18 facets
Peacock terms and undue emphasis9 facts · 2 facets
Performance Review Writing51 facts · 16 facets
Pitch Deck Writing60 facts · 14 facets
Policy and Governance Writing60 facts · 13 facets
Positive substitution style guides6 facts · 3 facets
Postmortem Writing58 facts · 15 facets
PRD Writing55 facts · 15 facets
Press Release Writing54 facts · 14 facets
Profile writing59 facts · 17 facets
Prompt-side control of LLM lexical tics30 facts · 6 facets
Proposal and Grant Writing50 facts · 18 facets
Public Speaking and Presentations73 facts · 17 facets
Pull Request Description Craft52 facts · 13 facets
README and changelog boilerplate tells5 facts · 3 facets
Release Blog and Launch Narrative54 facts · 17 facets
Resume and CV Writing55 facts · 17 facets
Rewriting with named sources and plain claims5 facts · 3 facets
Rhythm uniformity and burstiness5 facts · 2 facets
Runbook Craft66 facts · 18 facets
Sales and Marketing Copy84 facts · 25 facets
Significance inflation and promotional puffery6 facts · 5 facets
Source-domain collapse in LLM metaphor6 facts · 4 facets
Spec Writing73 facts · 19 facets
Speech Writing72 facts · 19 facets
Stylometry and AI-text detector limits5 facts · 3 facets
Support Ticket Writing72 facts · 19 facets
Survey Question Writing80 facts · 23 facets
Teaching Troubleshooting & Diagnostic Reasoning120 facts · 20 facets
Technical Assessment & Certification Design123 facts · 18 facets
Technical Instruction & Engineering Education19 facts · 5 facets
Technical Training Delivery & Developer Education32 facts · 7 facets
Term of art versus reflexive tic6 facts · 4 facets
Tic drift across model versions4 facts · 2 facets
Trailing participial analysis phrases6 facts · 3 facets
Travel-brochure and promotional register6 facts · 4 facets
Tricolon and rule-of-three lists4 facts · 2 facets
User Story and Acceptance Criteria71 facts · 14 facets
Vague attribution and promotional register in LLM prose32 facts · 6 facets
Vague attribution and weasel wording6 facts · 3 facets
Visual Writing57 facts · 14 facets
What-we-know / what-we-are-doing / next-update-at triple24 facts · 6 facets
Whitepaper Writing66 facts · 14 facets
Writing and Documentation128 facts · 34 facets
Data Analysis59 concepts
A/B Testing Fundamentals29 facts · 5 facets
anomaly detection89 facts · 32 facets
App Schemas integration for Siri AI15 facts · 3 facets
AppEntity content transfer and IntentValueRepresentation for Siri cross-app workflows13 facts · 4 facets
AppIntentsTesting harness for Siri schemas and entity integrations21 facts · 6 facets
Apple Intelligence accessibility and assistive workflows16 facts · 4 facets
Apple Intelligence availability and release matrix12 facts · 5 facets
Apple Intelligence communication summaries and prioritization13 facts · 2 facets
Apple Intelligence image edit provenance and export boundaries10 facts · 4 facets
Apple Intelligence Reports and user privacy controls9 facts · 5 facets
Apple Intelligence semantic indexing and content donations9 facts · 3 facets
Augmented Analytics and LLM-Assisted Analysis93 facts · 18 facets
Bayesian Data Analysis and Probabilistic Programming70 facts · 11 facets
Causal Discovery and Structure Learning104 facts · 18 facets
Cohort and Retention Analytics132 facts · 22 facets
Conformal Prediction and Uncertainty Quantification80 facts · 23 facets
Customer Lifetime Value Modeling69 facts · 21 facets
Customer-Facing and Embedded Analytics Dashboards70 facts · 21 facets
Data Acquisition and Sampling83 facts · 33 facets
Data Analysis11 facts · 4 facets
Data Analysis Foundations and Theory53 facts · 15 facets
Data Analysis Lifecycle86 facts · 28 facets
Data FinOps and Cost Optimization89 facts · 15 facets
Data Governance Catalogs and Discovery101 facts · 21 facets
Data Observability106 facts · 18 facets
Data Visualization71 facts · 17 facets
Deep Reinforcement Learning Foundations97 facts · 20 facets
Dimensional and Analytics Data Modeling90 facts · 19 facets
External intelligence and ChatGPT handoff consent14 facts · 3 facets
Genmoji and Image Wand integration9 facts · 3 facets
Geospatial Analytics117 facts · 24 facets
Image Playground generation and editing15 facts · 3 facets
Intelligent Photos editing and memory workflows15 facts · 5 facets
Knowledge Graphs and Semantic Analytics40 facts · 10 facets
Live Translation across Apple communication surfaces15 facts · 4 facets
Machine Learning66 facts · 33 facets
Managed Apple Intelligence and external intelligence controls12 facts · 4 facets
Marketing Mix Modeling and Incrementality86 facts · 18 facets
ML Model Monitoring16 facts · 5 facets
Network and Graph Analytics96 facts · 19 facets
Prescriptive Analytics and Optimization88 facts · 21 facets
Pricing and Revenue Analytics115 facts · 20 facets
Private Cloud Compute expansion to Google Cloud and NVIDIA10 facts · 4 facets
Private Cloud Compute trust architecture and verification15 facts · 5 facets
Product Analytics127 facts · 22 facets
Real-Time OLAP and Analytical Databases101 facts · 20 facets
Recommender Systems and Learning-to-Rank Analytics92 facts · 17 facets
Reporting and Communication34 facts · 7 facets
Reverse ETL and Operational Analytics109 facts · 22 facets
Semantic Layer and Headless BI100 facts · 16 facets
Shortcuts Use Model and intelligent automation15 facts · 4 facets
Siri AI personal context and onscreen awareness11 facts · 3 facets
Siri AI personalization and opt-in improvement data lifecycle17 facts · 3 facets
Siri app actions confirmation and contextual cues13 facts · 5 facets
Survival Analysis113 facts · 26 facets
Synthetic Data Generation119 facts · 24 facets
Text Analytics and NLP for Analysts109 facts · 22 facets
Visual Intelligence and Siri Camera workflows11 facts · 5 facets
Writing Tools and Write with Siri workflows16 facts · 4 facets
Local Model Performance Evaluation: Ollama, MLX, and Hardware Architectures29 concepts
16-bit Sub-channel Burst Framing2 facts · 1 facets
16-Bit Sub-Channel Bursts and Non-Sequential Tensor Bank Interleaving8 facts · 3 facets
Asymmetric KV Cache Quantization Algorithms2 facts · 2 facets
Bank Conflict Elimination in Non-Sequential Tensor Reads2 facts · 2 facets
Burst Truncation and Pipelined Prefetch Stalls2 facts · 2 facets
GDDR7 Channel Bandwidth and Peak Throughput2 facts · 1 facets
GDDR7 Four-Channel Interleaving Architecture2 facts · 2 facets
GEMM Compute Scaling vs GEMV Memory-Bandwidth Bounds2 facts · 1 facets
Gemma4-12B Cross-Platform Residency and Benchmarking4 facts · 3 facets
GGML Metal Kernel Dispatch and Command Buffer Offload2 facts · 2 facets
GGUF Alignment and Quantization Block Matrix2 facts · 1 facets
Inference Metrics Framework: TTFT TPS and Memory Profiling4 facts · 1 facets
Local Inference Acceleration: Memory Architectures, Metal Kernels, and Latency Optimization16 facts · 4 facets
Local Inference Micro-Architectures: Signaling, Quantization Superblocks, and Kernel Pipeline Scheduling16 facts · 4 facets
Local Model Performance Evaluation: Ollama, MLX, and Hardware Architectures20 facts · 6 facets
Metal Pipeline State Caching and Kernel Dispatch Bubbles2 facts · 2 facets
MLX KV Cache Quantization and Zero-Copy Pointer Passing2 facts · 2 facets
MLX Unified Memory vs eGPU GDDR7 Hardware Architecture4 facts · 4 facets
Multi-Token Prediction Heads and Speculative Decoding2 facts · 2 facets
Multi-Token Prediction Speculative Verification and Draft Amortization2 facts · 2 facets
Ollama Architecture and GGUF Memory-Mapping4 facts · 2 facets
PAM3 Modulation and GDDR7 Channel Interleaving2 facts · 2 facets
PCIe Protocol Tunneling and Thunderbolt Retimer Jitter2 facts · 2 facets
Qwen3.6-35B-MLX Sizing and Throughput Profiling4 facts · 1 facets
Shared Buffer Storage Modes and Zero-Copy Passing2 facts · 1 facets
SIMD Aligned Memory Vectorization and Super-block K-Quants2 facts · 2 facets
Thunderbolt 5 Bus Latency and Bandwidth Scaling Limit2 facts · 2 facets
TTFT Compute Bound Analysis and Inter-token Latency Jitter2 facts · 2 facets
Wired Memory Instrumentation and Static Activation Buffers2 facts · 1 facets
Finance, Markets & Blockchain15 concepts
401(k)/403(b) (match/vesting/Roth vs traditional)68 facts · 6 facets
ACA premium tax credits/APTC & CSRs53 facts · 6 facets
Bitcoin protocol and ecosystem17 facts · 5 facets
Budgeting and Saving78 facts · 17 facets
Consumer Finance19 facts · 5 facets
Estate Planning and Wills91 facts · 19 facets
Ethereum Consensus (Proof of Stake): Protocol-User Technical Reference185 facts · 27 facets
Health Insurance and Coverage107 facts · 18 facets
Investing and Retirement105 facts · 17 facets
Medical Debt and Billing154 facts · 33 facets
Personal Banking114 facts · 24 facets
Personal Income Taxes113 facts · 30 facets
Personal Insurance134 facts · 33 facets
Student Loans93 facts · 18 facets
Trading and Investing — Active Trading & How Financial Markets Work (Family Root)45 facts · 14 facets
DevOps, Infrastructure & Observability13 concepts
DevOps, Infrastructure & Observability2 facts · 1 facets
eBPF for Linux Observability, Networking & Security2 facts · 1 facets
Immutable & Atomic Linux Distributions — OSTree/rpm-ostree, bootc/CoreOS, NixOS, openSUSE MicroOS2 facts · 1 facets
Linux Boot & Init — UEFI/Secure Boot, GRUB, initramfs/dracut, Early Userspace88 facts · 15 facets
Linux Filesystems & Storage — ext4/XFS/Btrfs/ZFS, LVM, Block Layer & I/O Schedulers2 facts · 1 facets
Linux io_uring — Async I/O Rings, liburing, Registered Resources & Security-Disable Saga2 facts · 1 facets
Linux Kernel Architecture & Scheduling — CFS/EEVDF, Syscall ABI, Kernel Modules2 facts · 1 facets
Linux Mandatory Access Control & Privilege — SELinux, AppArmor & Capabilities2 facts · 1 facets
Linux Memory Management & NUMA — Virtual Memory, Paging, Reclaim, OOM, Hugepages, NUMA Tuning2 facts · 1 facets
Linux Package Management & Software Building — apt/dpkg, dnf/rpm, pacman, from-source & kernel build84 facts · 16 facets
Linux Sandboxing & Confinement — seccomp-bpf, Landlock, gVisor, Kata, Firecracker2 facts · 1 facets
Linux Virtualization — KVM, QEMU, libvirt, virtio & microVMs2 facts · 1 facets
systemd (init system & service manager)2 facts · 1 facets
Sciences & Human Behavior13 concepts
Applied Human Psychology20 facts · 6 facets
Behavioral Decision-Making and Cognitive Biases70 facts · 17 facets
Emotion & Affect Psychology154 facts · 19 facets
Health Behavior Change and Donor Registration20 facts · 5 facets
Learning & Expertise Psychology136 facts · 20 facets
Moral Psychology51 facts · 17 facets
Performance, Motivation & Resilience Psychology188 facts · 20 facets
Personality and Individual Differences99 facts · 22 facets
Persuasion & Influence Psychology (Attitude-Change Theory)75 facts · 18 facets
Psychology of Charitable Giving25 facts · 5 facets
Psychology of Human-AI Interaction (Trust & Appropriate Reliance)70 facts · 19 facets
Scientific Phylogenetics (ETE Toolkit)44 facts · 14 facets
Trust, Rapport & Psychological Safety82 facts · 14 facets
Personal Life & Property11 concepts
Auction Vehicle Repair Cost Estimation156 facts · 8 facets
AutoBidMaster International Bidding194 facts · 6 facets
Best-Value Used Car Selection116 facts · 6 facets
Copart Salvage Auctions225 facts · 6 facets
IAAI Salvage Auctions150 facts · 8 facets
Individual Buyer Best Practices at Salvage Auctions124 facts · 6 facets
Low-Cost Alternative Car-Buying Channels47 facts · 7 facets
Newbie Mistakes in Used Car Buying90 facts · 7 facets
Reading a Salvage Auction Listing172 facts · 7 facets
Salvage and Clean-Title Vehicle Valuation264 facts · 8 facets
Salvage Auction Bidding Strategy126 facts · 7 facets
Bucket catalog memory and closure reasons9 concepts
Bucket catalog memory and closure reasons66 facts · 7 facets
Bucket catalog stripes, state registry and eras17 facts · 4 facets
Dynamic bucket size cap under cache pressure17 facts · 5 facets
metaField cardinality and active-bucket count9 facts · 4 facets
serverStatus bucketCatalog and collStats timeseries counters8 facts · 3 facets
Side bucket catalog8 facts · 2 facets
Side bucket catalog for time series updates and deletes9 facts · 3 facets
Time series bucketing parameters: granularity, bucketMaxSpanSeconds, bucketRoundingSeconds8 facts · 5 facets
Time series cardinality and metaField design8 facts · 4 facets
Cluster Tier Limits and Feature Gates as Cost Drivers (Connections, IOPS Caps, Minimum Tiers)6 concepts
Atlas Infinite fixed per-tier IOPS and public-preview feature exclusions20 facts · 5 facets
Atlas Infinite fixed-IOPS tiers and decoupled storage15 facts · 5 facets
Atlas security add-on uplifts (auditing, LDAP, customer-managed keys, private endpoints)17 facts · 5 facets
Cluster Tier Limits and Feature Gates as Cost Drivers (Connections, IOPS Caps, Minimum Tiers)97 facts · 5 facets
Connection pool sizing and connection-storm control for Atlas (serverless and Lambda clients)18 facts · 4 facets
Connection pooling and connection-storm control for Atlas (serverless and Lambda clients)10 facts · 3 facets
Database Profiler vs Query Profiler6 concepts
$queryStats aggregation stage9 facts · 5 facets
Amazon DocumentDB profiler (CloudWatch Logs)19 facts · 5 facets
Atlas Real-Time Performance Panel17 facts · 5 facets
Database Profiler vs Query Profiler70 facts · 6 facets
Ops Manager Profiler20 facts · 7 facets
Percona PMM mongolog versus profiler query source18 facts · 6 facets
Bucket fragmentation remediation (re-insert/merge)5 concepts
Bucket fragmentation remediation (re-insert/merge)70 facts · 7 facets
Bucket reopening and the {metaField, timeField} index requirement8 facts · 3 facets
Cache-pressure early bucket closure and bucket catalog memory13 facts · 4 facets
Delete and re-insert safety on time series12 facts · 3 facets
Sharded time series rebuild and resharding16 facts · 5 facets
Business & Enterprise5 concepts
Personal Venture — NC Organ-Donation Nonprofit & Founder Toolkit143 facts · 21 facets
Semantic Monitoring, Reporting & Customer Dashboards for TAM (value-chain synthesis)32 facts · 10 facets
TAM commercial metrics73 facts · 21 facets
TAM Expertise52 facts · 13 facets
Value Realization and Outcome-Based Customer Success74 facts · 21 facets
Covered queries on sharded collections5 concepts
Covered queries on sharded collections45 facts · 6 facets
Hashed and compound hashed shard keys and index coverage6 facts · 3 facets
Orphaned documents and range deletion11 facts · 3 facets
Reading sharded explain output (shards, SINGLE_SHARD, SHARD_MERGE)10 facts · 4 facets
SHARDING_FILTER stage and chunkSkips7 facts · 3 facets
Independent shard scaling and per-shard tiering5 concepts
Atlas compute auto-scaling for sharded clusters9 facts · 3 facets
Balancer data-size policy and zone-aware migration8 facts · 4 facets
Hot shard diagnosis and shard key remediation10 facts · 4 facets
Independent shard scaling and per-shard tiering63 facts · 7 facets
Per-shard compute auto-scaling rules and limits on Atlas13 facts · 5 facets
Atlas Vector Search automatic quantization and rescoring4 concepts
Atlas Vector Search automatic quantization and rescoring69 facts · 7 facets
Automated Embedding (autoEmbed) quantization types14 facts · 5 facets
Automated Embedding (autoEmbed) quantization types including binaryNoRescore8 facts · 2 facets
Quantization-aware and Matryoshka embeddings (voyage-3-large) with Atlas dimension slicing20 facts · 4 facets
Index build resource limits (maxNumActiveUserIndexBuilds, disk space)4 concepts
Atlas index build tier defaults10 facts · 6 facets
Atlas tier-fixed index build limits9 facts · 4 facets
Index build resource limits (maxNumActiveUserIndexBuilds, disk space)63 facts · 6 facets
Primary-driven index builds (spill to a replicated table)16 facts · 4 facets
Atlas storage auto-scaling and disk reclaim via compact3 concepts
Atlas Infinite storage model (max storage limit, no auto-scaling)17 facts · 6 facets
Atlas storage auto-scaling and disk reclaim via compact72 facts · 7 facets
MongoDB 8.0 autoCompact background compaction on Atlas20 facts · 6 facets
Resumable index builds3 concepts
MongoDB primary-driven index builds (PDIB)15 facts · 5 facets
Primary-driven index builds9 facts · 3 facets
Resumable index builds76 facts · 7 facets
SORT_MERGE and $in sort expansion3 concepts
Interval evaluation trees and parameterized plan caching16 facts · 5 facets
Multiplanner scoring and tie-breakers9 facts · 3 facets
SORT_MERGE and $in sort expansion56 facts · 7 facets
Awesome TUIs catalog and terminal user interface design2 concepts
Awesome TUIs catalog and terminal user interface design65 facts · 5 facets
Terminal user interface interaction and architecture65 facts · 5 facets
Hidden indexes and safe index removal2 concepts
Hidden indexes and safe index removal71 facts · 6 facets
Shard key index constraints when dropping or hiding indexes13 facts · 2 facets
Oplog sizing under storage auto-scaling2 concepts
Oplog sizing under storage auto-scaling65 facts · 8 facets
replSetResizeOplog and oplog compaction runbook18 facts · 6 facets
Platform Consolidation TCO (Atlas Search/Vector Search vs Separate Search or Vector DB)2 concepts
Idle-spend and minimum-commit economics of serverless vector stores20 facts · 5 facets
Platform Consolidation TCO (Atlas Search/Vector Search vs Separate Search or Vector DB)65 facts · 7 facets
Read Offload via Caching and Precomputed Views ($merge/$out, Computed Pattern)2 concepts
Read Offload via Caching and Precomputed Views ($merge/$out, Computed Pattern)78 facts · 8 facets
WiredTiger cache sizing and working-set fit6 facts · 3 facets
Replanning loops and replanReason2 concepts
Replanning loops and replanReason37 facts · 7 facets
SBE plan cache pinned entries and the classic runtime planner for SBE14 facts · 4 facets
Rolling index builds2 concepts
Atlas Administration API rolling index endpoint16 facts · 3 facets
Rolling index builds73 facts · 7 facets
Unused index detection with $indexStats2 concepts
dropIndexes locking and rollback by rebuild8 facts · 4 facets
Unused index detection with $indexStats64 facts · 5 facets
WiredTiger cache eviction and dirty ratio2 concepts
Eviction thread sizing and wiredTigerEngineRuntimeConfig tuning19 facts · 5 facets
WiredTiger cache eviction and dirty ratio67 facts · 7 facets
Awesome TUIs project catalog1 concept
Awesome TUIs project catalog718 facts · 3 facets
Long-running secondary reads in sharded clusters1 concept
Long-running secondary reads in sharded clusters66 facts · 7 facets
Migration and Cutover Cost (Live Migration, mongosync, Dual-Running, Egress)1 concept
Migration and Cutover Cost (Live Migration, mongosync, Dual-Running, Egress)89 facts · 7 facets
Operation rejection filters1 concept
Operation rejection filters64 facts · 7 facets
Shard Key Design and Resharding as Cost Levers1 concept
Shard Key Design and Resharding as Cost Levers77 facts · 7 facets