How real projects summarise themselves for language models.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
AnswerDotAIllms.txtAnswerDotAI/fastcore/nbs/llms.txt
show a function's real parameters in place of `**kwargs`, for IDEs and generated documentation. - Use fastcore's versions of `ThreadPoolExecutor` and `ProcessPoolExecutor` for simpler concurrent processing. - Prefer fastcore
Steady2 mentions in 2 weeks
No other project uses it yet
datacontractllms.txtdatacontract/datacontract-cli/llms.txt
entry point for the project's GitHub repository and README. The complete documentation is a separate site with its own, much larger llms.txt. - Contract format: the [Open Data Contract Standard
No other project uses it yet
gdsfactoryllms.txtgdsfactory/gdsfactory/docs/llms.txt
printable objects. It outputs CAD files (GDS, OASIS, STL, GERBER) from Python code. ## Documentation - [Getting Started](https://gdsfactory.github.io/gdsfactory/getting_started.html): Installation, setup, and prerequisites - [Layout](https://gdsfactory.github.io/gdsfactory/layout.html): Core layout concepts
hareharePipes a download into a shellllms.txtharehare/mq/docs/llms-full.txt
Workflows**: Efficiently manipulate and process Markdown used in LLM prompts and outputs - **Documentation Management**: Extract, transform, and organize content across multiple documentation files - **Content Analysis**: Quickly extract specific sections
No other project uses it yet
hareharellms.txtharehare/mq/docs/llms.txt
easily slice, filter, map, and transform structured Markdown data. Especially useful for LLM workflows, documentation management, content analysis, and batch processing. ## Docs - [Introduction](https://mqlang.org/book/): Overview, features
christo-auerllms.txtchristo-auer/eilmeldung/docs/llms.txt
configurable). ## Lesser-Known Features Many useful features are not obvious from the basic documentation. Here is a curated list: - **Link hints** (`; ;`): Press `; ;` in the article content panel and letter hints
adridallms.txtadrida/tracer/llms.txt
python -m pip install -e . The published package may not contain the source changes documented here. ## Core API (4 functions) tracer.fit("traces.jsonl", embeddings=X) → FitResult tracer.load_router(".tracer", embedder
invertasellms.txtinvertase/react-native-google-mobile-ads/llms.txt
Google Ad Manager), including Expo support. ## Primary guidance - [Integrator instructions](https://raw.githubusercontent.com/invertase/react-native-google-mobile-ads/main/packages/core/AGENTS.md) - [Documentation](https://docs.page/invertase/react-native-google-mobile-ads) - [Documentation llms.txt](https://docs.page/invertase/react-native-google-mobile-ads/llms.txt) - [Generated API reference](https://invertase.github.io/react-native-google-mobile-ads/) - [Source repository
Steady2 mentions in 2 weeks
No other project uses it yet
sirkirbyllms.txtsirkirby/unifi-network-mcp/docs/llms.txt
only within the tool family that returned them unless an explicit resolver documents a verified bridge. ## Getting Started - [Quick start](https://github.com/sirkirby/unifi-mcp/blob/main/QUICKSTART.md): Install and configure a local MCP server
NVIDIAllms.txtNVIDIA/cudnn-frontend/llms.txt
SDPA/Flash Attention, MoE grouped-GEMM fusions, fused normalizations) for Hopper and Blackwell GPUs. Published documentation: https://docs.nvidia.com/deeplearning/cudnn/latest/developer/overview.html ## Start here - [README](https://github.com/NVIDIA/cudnn-frontend/blob/main/README.md): overview, installation, feature highlights - [AGENTS.md
Electricitysheepllms.txtElectricitysheep/dsh-handbook/llms-full.txt
guide, plugin development, plugin 开发, sandbox security, cache hit rate, cost optimization, agent benchmark. ## Documentation - [Chinese README (canonical)](README.md) - [English README](README.en.md) - [Online docs site (searchable)](https://electricitysheep.github.io/dsh-handbook/) - [Cheatsheet
Electricitysheepllms.txtElectricitysheep/dsh-handbook/llms.txt
guide, plugin development, plugin 开发, sandbox security, cache hit rate, cost optimization, agent benchmark. ## Documentation - [Chinese README (canonical)](README.md) - [English README](README.en.md) - [Online docs site (searchable)](https://electricitysheep.github.io/dsh-handbook/) - [Cheatsheet
Vrun-designllms.txtVrun-design/openflowkit/public/llms.txt
only the canvas changes, canonically numbered. "The box I selected" is `selection` in `get_document`. ## Draw this repo's architecture `discover_architecture` with `{ path }` proposes a C4 workspace (`dsl`) from
umputunllms.txtumputun/revdiff/site/llms.txt
revdiff > TUI for reviewing diffs, files, and documents with inline annotations revdiff is a terminal-based UI for code review and document annotation. It displays diffs from Git, Mercurial
JuliusBrusseellms.txtJuliusBrussee/caveman-code/llms.txt
backed memory. This file is the LLM-friendly entry point to Caveman Code's documentation. Each linked page is plain markdown. ## Install ``` npm install -g @juliusbrussee/caveman-code ``` Requires Node.js 20+. Binaries
GarethManningllms.txtGarethManning/claude-education-skills/llms.txt
planned three-layer education AI system (skill library → context engine → orchestrator). ## Key Documentation - [README.md](https://github.com/GarethManning/education-agent-skills/blob/main/README.md): Full overview, architecture, usage, and domain table - [ARCHITECTURE.md](https://github.com/GarethManning/education-agent-skills/blob/main/docs/ARCHITECTURE.md): Three-layer
fluffyponyPipes a download into a shellllms.txtfluffypony/dothething/llms.txt
working until the job is finished. It handles research, analysis, report writing, data extraction, document processing, and system administration. Licensed under BSD 3-Clause. dothething routes all model calls through
fscorruptllms.txtfscorrupt/posterizarr/docs/llms.txt
multi-process lifecycle, run modes, database schemas, rendering engine, REST endpoints, and conventions. ## Core Documentation & Deployment - [Requirements](https://fscorrupt.github.io/posterizarr/requirements/): Host prerequisites including ImageMagick 7, PowerShell 7+, Python 3.13, memory
open-webuillms.txtopen-webui/docs/static/llms.txt
Open WebUI Docs Open WebUI documentation is available as regular HTML and raw Markdown. Start at https://docs.openwebui.com/sitemap.xml to discover pages. For any docs page, append `.md` for Markdown
CodeAbrallms.txtCodeAbra/iai-personal-memory-engine/llms.txt
install --with-tools` from a source checkout. See [docs/DEPLOYMENT.md](docs/DEPLOYMENT.md). ## Docs - [README.md](README.md): full documentation, English. - [README_zh-CN.md](README_zh-CN.md): Chinese. - [CHANGELOG.md](CHANGELOG.md): release history. - [docs/DEPLOYMENT.md](docs/DEPLOYMENT.md): deployment. - [docs/EMBEDDERS.md](docs/EMBEDDERS.md): swappable embedders
A markdown file at a website's root that gives language models a short guide to the site and links to the pages worth reading.
The same idea with the content included, so an agent can read the documentation in one request.
Agents and tools that fetch documentation on someone's behalf. It's a proposal, not a standard, and support varies.
Start with a one-line summary, then sections of links with a sentence each. The examples here show what real projects do.
