How real projects summarise themselves for language models.
malamutemayhemllms.txtmalamutemayhem/unclick/public/llms.txt
compatible agent-rails layer where AI agents discover tools, load memory, use secure connections, run crews, and verify work with the Pass family. One GitHub release package gives access
matterhornsollms.txtmatterhornso/subscribetome/docs/llms.txt
subscribetome > Open-source API-key security for AI coding agents: keys live in your OS > keychain, and a local credential broker injects them into outbound HTTP > calls — so the agent
Moai-Team-LLCllms.txtMoai-Team-LLC/AgenticMind/docs/llms.txt
construction](https://agenticmind.moaiteam.com/blog/safe-by-construction/): fail-closed scoped tokens, RLS tenant isolation, local embeddings. - [Security model](https://agenticmind.moaiteam.com/security-model/): auth (fail-closed bearer), least-privilege scopes, Postgres RLS, data residency. ## Agent
mstuartllms.txtmstuart/tare/llms.txt
tareMiddleware`, `startProxy` (+ prebuilt binaries). ## Docs - [README](README.md): overview, install, benchmarks, comparison, status. - [CONTRIBUTING](CONTRIBUTING.md), [SECURITY](SECURITY.md), [CHANGELOG](CHANGELOG.md). ## Key facts - AST code skeletonization: 59–73% token reduction on the committed
namanxdevllms.txtnamanxdev/MCPHub/public/llms.txt
pipeline?" - "How do I audit an MCP server for auth, transport, and tool-poisoning security issues?" - "How do I test a local (stdio) MCP server from a hosted
node0networkllms.txtnode0network/node0/llms-full.txt
Parameters: `query` (string). * **`node0_explain`**: Summarize node0 specifications. Parameters: none. ### 6.2 node0-agent (Local / Secure Key storage) * **`node0_identity`**: Generate or load local keypair. Parameters: `action` (string, either "generate", "show
node0networkllms.txtnode0network/node0/llms.txt
tier progressive verification ladder. Ephemeral keys generate in 1 second. Permanent directory registry is secured via scrypt Proof-of-Work. * **Subjective Trust:** Graph-based peer vouching, local anchor rule
papperrollinggeryllms.txtpapperrollinggery/delegate-to-deepseek-harness/llms.txt
code, and review. - [Chinese use-case cookbook](https://github.com/papperrollinggery/delegate-to-deepseek-harness/blob/main/docs/use-cases.zh-CN.md): Simplified Chinese scenario guide. - [Security policy](https://github.com/papperrollinggery/delegate-to-deepseek-harness/blob/main/SECURITY.md): invariants, limitations, and private disclosure guidance. - [Contributing guide](https://github.com/papperrollinggery/delegate-to-deepseek-harness/blob/main/CONTRIBUTING.md):
parousia8888llms.txtparousia8888/web-app-security-skill/llms.txt
Security Skill A Claude Code skill for web application security: a nine-phase audit and hardening program, three read-only audit scripts, and a decision model for what the public
phaneron-roboticsllms.txtphaneron-robotics/scry/docs/llms.txt
/scry/reference/permissions/) ## Legal - [Privacy policy](https://phaneron-robotics.github.io/scry/legal/privacy/) - [Play Store Data Safety](https://phaneron-robotics.github.io/scry/legal/data-safety/) - [Security policy](https://phaneron-robotics.github.io/scry/legal/security/) - [License](https://phaneron-robotics.github.io/scry/legal/license/)
qmmughalllms.txtqmmughal/AgentWire/llms.txt
Wireshark + Cloudflare for AI Agents. AgentWire is a 100% free and open-source observability, security, and governance platform designed specifically for AI Agents, Large Language Models (LLMs), and Model Context
Quarktexllms.txtQuarktex/qcobrain/llms.txt
propose changes; the one non-negotiable is that every write honors cite-or-refuse. - [Security](SECURITY.md): What stays local vs. leaves your machine, secret handling, and private disclosure. - [Changelog](CHANGELOG.md
Raknaosllms.txtRaknaos/lightpanda-session-bridge/llms-full.txt
passkeys, hardware keys (FIDO2), or Google/Microsoft SSO. Providing plaintext passwords to LLMs presents critical security risks (exfiltration, prompt injection, credential leakage across logs and context windows). ## 2. Solution Overview
Raknaosllms.txtRaknaos/lightpanda-session-bridge/llms.txt
Chromium-based desktop browser (Chrome, Edge, Brave, Opera, Vivaldi, Arc, Comet). The extension securely captures scoped cookies for the active origin upon explicit user interaction. - **Strict SSRF Firewall:** The local
rishapgandhillms.txtrishapgandhi/python-skills/llms.txt
generate consistent, production-quality Python code. ## Skills - Code Style: skills/common/code-style.md - Testing: skills/common/testing.md - Security: skills/common/security.md - API Auth: skills/common/api-auth.md - Database Design: skills/common/db-design.md - Error Handling: skills/common/error-handling.md - Performance: skills/common/performance.md - FastAPI: skills/fastapi/SKILL.md - Django: skills/django/SKILL.md
runcyclesllms.txtruncycles/cycles-docs/public/llms.txt
Metrics, dashboards, and alerts - [Observability Setup](https://runcycles.io/how-to/observability-setup): Prometheus, Grafana, and Datadog integration - [Security Hardening](https://runcycles.io/how-to/security-hardening): Security best practices - [Testing](https://runcycles.io/how-to/testing-with-cycles): Testing strategies for Cycles
sayed3li97llms.txtsayed3li97/skillscore/docs/llms.txt
/sayed3li97/skillscore/blob/main/CHANGELOG.md): release history ## Optional - [pub.dev package](https://pub.dev/packages/skillscore): install page and API docs - [SECURITY](https://github.com/sayed3li97/skillscore/blob/main/SECURITY.md): private vulnerability reporting
schubydoollms.txtschubydoo/clauster/docs/llms.txt
auth/bind matrix, TLS, reverse proxies. Read this before any LAN or remote-exposure answer. - [Security](https://schubydoo.github.io/clauster/latest/security/): fail-closed auth, headers, workspace trust, log redaction, SSRF and bypassPermissions gates
snapsynapsellms.txtsnapsynapse/graceful-boundaries/llms-full.txt
traffic. A proactive discovery endpoint prevents the first round of 429s entirely. 2. **Expose security intent.** The `why` field is not a courtesy — it is a security signal. When
snapsynapsellms.txtsnapsynapse/graceful-boundaries/llms.txt
readers - `llms-full.txt`: generated full text of the specification and adoption documents - `/.well-known/security.txt`: RFC 9116 security contact - `/.well-known/assistant-guide.txt`: GuideCheck assistant guide for bounded contributor work - `assistant-guide.txt`: repository-local copy
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.
