How real projects summarise themselves for language models.
OthmanAdillms.txtOthmanAdi/codebase-knowledge-builder/llms.txt
example](https://github.com/OthmanAdi/codebase-knowledge-builder/blob/main/examples/distribution-architecture.md): source-cited analysis of the repository's own distribution architecture - [Security policy](https://github.com/OthmanAdi/codebase-knowledge-builder/blob/main/SECURITY.md): private vulnerability reporting and safe reproduction guidance ## Product boundary Codebase Knowledge
ssdeanxllms.txtssdeanx/secure-rag-multi-agent/llms.txt
Mastra Governed RAG > A secure, enterprise-grade Retrieval-Augmented Generation (RAG) system built with Mastra AI orchestration framework, implementing role-based access control (RBAC) with hierarchical permissions, document classification
alexfrmnllms.txtalexfrmn/murmur/site/llms-full.txt
recipient, status, timestamp and nonce. Unsigned, stale, replayed and wrong-recipient ACKs are rejected. ## Security model - End to end: messages are encrypted by the sender and decrypted only
alexfrmnllms.txtalexfrmn/murmur/site/llms.txt
server) - [Protocol v1](https://github.com/alexfrmn/murmur/blob/main/docs/protocol-v1.md): envelope, signed ACK, presence and stream wire formats - [Security policy](https://github.com/alexfrmn/murmur/blob/main/SECURITY.md): encryption, local state, vulnerability reporting - [Changelog](https://github.com/alexfrmn/murmur/blob/main/CHANGELOG.md): release history
cameronryellms.txtcameronrye/activitypub-mcp/public/llms-full.txt
source tree - **Cross-Platform Support**: Works on Windows, macOS, and Linux (Node 20+ required) - **Security-Hardened**: SSRF guard on every outbound call (full IPv4 + IPv6 private-range blocking), streaming response
cameronryellms.txtcameronrye/activitypub-mcp/public/llms.txt
Cross-Platform Support**: Works on Windows, macOS, and Linux (Node 20+) - **Security-Hardened**: SSRF guard on all outbound calls, streaming response-size caps, instance blocklist, thread cross-origin gating, audit
cfircoollms.txtcfircoo/claude-code-toolkit/docs/llms.txt
hooks, and commands that supercharge your Claude Code IDE with AI-powered automation and security guardrails. ## Getting Started - [Installation Guide](https://github.com/cfircoo/claude-code-toolkit#automatic-installation-recommended): Quick setup with `./install.sh` (installs everything
enkhbold470llms.txtenkhbold470/bci-mcp/llms.txt
tests and open a pull request. - [Changelog](https://raw.githubusercontent.com/enkhbold470/bci-mcp/main/docs/changelog.md): Release history. - [Security](https://raw.githubusercontent.com/enkhbold470/bci-mcp/main/docs/security.md): Threat model and vulnerability reporting. ## Interactive - [DeepWiki](https://deepwiki.com/enkhbold470/bci-mcp): Ask questions about
Hedgy-Labsllms.txtHedgy-Labs/setoku/site/llms.txt
setoku.com/docs): the HTTP API, authentication, the MCP tool surface, quickstart, and the security model. Markdown twin: [/docs.md](https://setoku.com/docs.md). - [Setoku homepage in markdown](https://setoku.com/index.md): the whole
heymillms.txtheymi/aldus-palace/llms-full.txt
call cannot leave the device unredacted. **Designed next** — local encrypted storage (Keychain / Secure Enclave). ## Where the difficulty lives **Models return text. Code needs records.** A model writes `"0.8"` where
jorekaillms.txtjorekai/db-timetable-mcp/llms.txt
contract. - [docs/data-model.md]: Meaning of planned, changed and effective event values. - [docs/architecture.md]: Components, transports and security model. - [src/server.ts]: MCP server factory. - [src/api/timetableParser.ts]: XML validation and semantic normalization. ## Key concepts - Use `getStationBoard
LeonTing1010llms.txtLeonTing1010/tap/docs/llms.txt
tiers, when introduced, will require a named first paying customer + named feature shipping atomically. ## Security invariants - Taprun servers never push executable code to clients. - Taprun servers never initiate connections
mimnetsllms.txtmimnets/OpenHRApp/public/llms-full.txt
# OpenHRApp > OpenHRApp is free, open-source HR management software for small and mid-sized
shintenillms.txtshinteni/prompt-island/docs/llms.txt
shinteni.github.io/prompt-island/install.html - Privacy: https://shinteni.github.io/prompt-island/privacy.html - FAQ: https://shinteni.github.io/prompt-island/faq.html - Support: https://shinteni.github.io/prompt-island/support.html - Security reporting metadata: https://shinteni.github.io/prompt-island/.well-known/security.txt ## Language Versions - English: https://shinteni.github.io/prompt-island/en/ - Japanese: https://shinteni.github.io/prompt-island/ja/
Xquik-devllms.txtXquik-dev/xquik-docs/llms.txt
docs.xquik.com/guides/troubleshooting) - [Type Definitions](https://docs.xquik.com/guides/x-api-typescript-types) - [Open Source Assurance](https://docs.xquik.com/guides/open-source-assurance) - [Security](https://docs.xquik.com/security)
agencyenterprisellms.txtagencyenterprise/fathom-mcp-server/public/llms-full.txt
hosts (like Claude Desktop) to access Fathom AI meeting data. It acts as a secure bridge between AI assistants and Fathom AI's meeting recording and transcription service. Think
agencyenterprisellms.txtagencyenterprise/fathom-mcp-server/public/llms.txt
hosts (like Claude Desktop) to access Fathom AI meeting data. It acts as a secure bridge between AI assistants and Fathom AI's meeting recording and transcription service. Think
ashlraillms.txtashlrai/phantom-secrets/docs/llms-full.txt
vault API receives ciphertext rather than decrypted secret values; client, account, endpoint, and deployment security remain in scope. - `phantom_cloud_pull` — After commissioning, pull a vault snapshot. Params: force, confirm
bntvllntllms.txtbntvllnt/agent-skills/llms-full.txt
bntvllnt.com/github) — issues, PRs, code - [X / Twitter](https://bntvllnt.com/x) — updates, DMs for security - [LinkedIn](https://bntvllnt.com/linkedin) — professional inquiries - [Book a meeting](https://bntvllnt.com/book) — consultation, collaboration, or anything
bntvllntllms.txtbntvllnt/agent-skills/llms.txt
ship, fix, review, done - [tmux](tmux/SKILL.md): Terminal multiplexer — sessions, windows, panes, layouts, scripting ## Optional - [Security Policy](SECURITY.md): Vulnerability reporting and disclosure policy - [Code of Conduct](CODE_OF_CONDUCT.md): Community guidelines - [License](LICENSE
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.
