How real projects summarise themselves for language models.
openqa-cnllms.txtopenqa-cn/codexqa/llms.txt
report. - [codexqa-requirement-analyzer](skills/codexqa-requirement-analyzer/README.md): Quality, ambiguity, and conflict analysis of PRD and requirement documents into a gap register. - [codexqa-testcase-generator](skills/codexqa-testcase-generator/README.md): Generate manual test plans and cases (Plan
ssdeanxllms.txtssdeanx/AgentStack/llms.txt
Mastra core (agents, tools, workflows, networks, MCP/A2A servers), frontend UI (Next.js app + shadcn/ui components), documentation, examples, and tests. Use the sections below to quickly find core docs, specs, examples
nvwaljllms.txtnvwalj/ai-memory-reader/llms.txt
/.kimi/` | Plus any custom folder added via the `+` button in the sidebar. ## Key documentation - Repo: https://github.com/nvwalj/ai-memory-reader - Landing page: https://nvwalj.github.io/ai-memory-reader/ - Memory location guide: https://nvwalj.github.io/ai-memory-reader/claude-code-memory-guide.html - Release
Perseus-Computing-LLCllms.txtPerseus-Computing-LLC/perseus/llms.txt
control, company-run or independent status, limitation, and source. Product behavior, benchmark evidence, security documentation, and procurement posture are separate claim classes
crp4222llms.txtcrp4222/PrivAiTe/docs/llms.txt
validity guards - [COMPARISON.md](https://github.com/crp4222/privaite-bench/blob/main/COMPARISON.md): reproducible detection benchmark on 120 real AI4Privacy documents. onnx preset 84.9% span recall and 81.0% strict, 2/14 false positives, 15.1% tool-call leak versus
crp4222llms.txtcrp4222/PrivAiTe/llms-full.txt
PrivAiTe, full documentation > Concatenated project documentation for LLM consumption. The map with > one-line summaries per page is in llms.txt. Regenerated at each release. --- # PrivAiTe Self-hosted PII redaction proxy
fullbleed-enginellms.txtfullbleed-engine/fullbleed-official/llms.txt
Fullbleed PDF Engine > Fullbleed 2.3.1 is a deterministic, self-contained document-generation runtime for Python and Rust. It turns structured data plus static HTML/CSS into validated PDF documents without
Kewtonllms.txtKewton/CommandMate/website/llms.txt
someone's head. It is installed as Skills and read by the agent. ## Docs - [Documentation](https://github.com/Kewton/CommandMate/tree/main/docs/en): the English docs - [Tutorial](https://github.com/Kewton/CommandMate/blob/main/docs/en/user-guide/tutorial.md): Use a sample repository with
nirholasllms.txtnirholas/universal-crypto-mcp/llms.txt
Polygon, BSC, and testnets. ## Links - Repository: https://github.com/nirholas/universal-crypto-mcp - Author: https://github.com/nirholas - Full documentation: https://raw.githubusercontent.com/nirholas/universal-crypto-mcp/main/llms-full.txt
nirholasllms.txtnirholas/universal-crypto-mcp/x402/llms.txt
PAYMENT) - Monitor transactions via x402_tx_status - Keep minimal balance in hot wallet ## Documentation - docs/QUICKSTART.md - 5-minute setup - docs/MCP_TOOLS.md - Full tool reference - docs/ARCHITECTURE.md - Protocol deep dive - docs/EXAMPLES.md - Real-world examples
OnlyCLIllms.txtOnlyCLI/OnlyCLI/docs/llms.txt
support, pagination, streaming, retries, and shell completion. ## Best starting points - Homepage: https://onlycli.github.io/OnlyCLI/ - Documentation: https://onlycli.github.io/OnlyCLI/docs/ - GitHub repository: https://github.com/onlycli/onlycli ## Key product pages - Token cost benchmark
HimanshuJ16llms.txtHimanshuJ16/Algo-Trading-Skills/llms-full.txt
Algo-Trading-Skills — Extended Documentation for LLM Context Windows ## Overview Algo-Trading-Skills is an open-source engineering library of algorithmic trading playbooks in the agentskills.io format, written
HimanshuJ16llms.txtHimanshuJ16/Algo-Trading-Skills/llms.txt
15c3-5, Reg NMS, EU MiFID II / RTS 6, UK FCA, SEBI, ISDA). ## Core Documentation - [README.md](README.md): Repository overview, quick start, domain breakdown, and compatible platforms. - [AGENTS.md](AGENTS.md): Open cross
jmrplensllms.txtjmrplens/gitlab-mcp-server/llms-full.txt
actions use project_id* or group_id*. Personal token actions use user_id where documented, and self actions take no scope ID. Deploy token/key delete and token revoke are irreversible
jmrplensllms.txtjmrplens/gitlab-mcp-server/llms.txt
contribution events breakdow... - weekly_team_recap: Generate a comprehensive weekly recap for a team. ## Documentation - [Documentation site index](https://jmrp.io/docs/gitlab-mcp-server/llms.txt): Index of every published documentation page, which is what
mshadmanrahmanllms.txtmshadmanrahman/claudecode-guide/public/llms-full.txt
didn't help: - Check the Troubleshooting page for common fixes - Visit [Anthropic's official documentation](https://docs.anthropic.com/en/docs/claude-code) for the latest setup instructions - Search the [Claude Code GitHub issues
mshadmanrahmanllms.txtmshadmanrahman/claudecode-guide/public/llms.txt
Summarize Any Webpage](https://claudecodeguide.dev/for-chrome/summarize-any-webpage-with-claude): Get the key points from any article or document. - [Research Any Topic](https://claudecodeguide.dev/for-chrome/research-any-topic-with-claude): Use Claude to research while you browse. ## Claude
Ryan-yang125llms.txtRyan-yang125/motion-lexicon/public/llms-full.txt
motion-lexicon.pages.dev/en/blocks/developer-docs/): Organizes installation, code comparison, command search, and preview output into navigable developer documentation. [Registry](https://motion-lexicon.pages.dev/r/developer-docs.json) - [Media editorial](https://motion-lexicon.pages.dev/en/blocks/media-editorial/): Browses a complete visual feature through
sandraschillms.txtsandraschi/windows-computer-use-mcp/llms-full.txt
windows-computer-use-mcp — Full Documentation Windows **computer use agent**: structured native UI automation via Pywinauto/UIA. Read docs/SAFETY.md before production use. ## Tools ### analyze_winapp (NEW) Auto-crawl a Windows
almogdepazllms.txtalmogdepaz/wolfpack/site/llms.txt
broker and survive web-server restarts. ## Start here - Homepage: https://almogdepaz.github.io/wolfpack/ - Source and documentation: https://github.com/almogdepaz/wolfpack - Quickstart: https://github.com/almogdepaz/wolfpack#quickstart - Full agent-readable summary: https://almogdepaz.github.io/wolfpack/llms-full.txt
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.
