How real projects summarise themselves for language models.
quinnjrllms.txtquinnjr/claude-code-profiles/docs/llms-full.txt
configuration. Each profile is a complete, isolated Claude Code configuration directory containing settings.json, .credentials.json, MCP server configs, CLAUDE.md, plugins, and history. License: MIT Repository: https://github.com/quinnjr/claude-code-profiles Website: https://quinnjr.github.io
quinnjrllms.txtquinnjr/claude-code-profiles/docs/llms.txt
configuration. Each profile is a complete, isolated Claude Code configuration directory containing settings.json, .credentials.json, MCP server configs, CLAUDE.md, plugins, and history. ## Documentation - [Landing page](https://quinnjr.github.io/claude-code-profiles/): Features, install instructions
tenuo-aillms.txttenuo-ai/tenuo/docs/llms.txt
tenuo.ai/google-adk): Warrant-based authorization for ADK agents - [MCP](https://tenuo.ai/mcp): Secure MCP clients and servers with warrants and argument constraints - [A2A](https://tenuo.ai/a2a): Warrant-based authorization
2389-researchllms.txt2389-research/claude-plugins/docs/llms.txt
Research Claude Code Plugin Marketplace > Open source Claude Code plugins and MCP servers from 2389 Research Inc. Development workflows, testing, system administration, and AI agent capabilities. Install with one command
growthack88llms.txtgrowthack88/growth-marketing-os/llms.txt
original, battle-tested AI marketing assets: prompts, Claude skills, AI agents, custom GPTs, MCP recipes, n8n/Make automation workflows, growth playbooks, frameworks, and bilingual (English + Arabic) swipe files. Created and maintained
vouchdevllms.txtvouchdev/vouch/llms.txt
vouch > Git-native, review-gated knowledge base for LLM agents. MCP server + JSONL tool server + CLI. Agents propose writes; humans approve them with `vouch approve`. Approved artifacts land as plain
yfedoseevllms.txtyfedoseev/browser_oxide/llms.txt
crates are `publish = false` pending a single-crate release - Python: `pip install browser-oxide` - MCP server (for AI agents): `cargo install --git https://github.com/yfedoseev/browser_oxide browser_oxide_mcp` → `browser-oxide
hyperb1issllms.txthyperb1iss/lucidity-mcp/docs/llms-full.txt
Each client may support different MCP features, allowing for varying levels of integration with MCP servers. ## Feature support matrix | Client | [Resources] | [Prompts] | [Tools] | [Sampling] | Roots | Notes | | ------------------------------------ | ----------- | --------- | ------- | ---------- | ----- | ------------------------------------------------------------------ | | [Claude Desktop App][Claude
hongnoulllms.txthongnoul/hwatu/llms.txt
JSON protocol over a Unix socket, a CLI mirroring it, and `hwatu mcp`, a Model Context Protocol server over stdio for Claude Code, Cursor, and other MCP clients. Agent-facing
ThreeMoonsLabllms.txtThreeMoonsLab/agents-shipgate/llms-full.txt
gate for AI-generated agent capability changes. Reads `shipgate.yaml` plus tool sources (MCP exports, MCP server source (TypeScript/Go registration idioms), OpenAPI specs, OpenAI Agents SDK Python files, Anthropic Messages
ThreeMoonsLabllms.txtThreeMoonsLab/agents-shipgate/llms.txt
invoke models. - Does not run agents. - Does not call tools. - Does not connect to MCP servers. - Does not make scanner network calls by default. - Does not collect scanner telemetry
major7appsllms.txtmajor7apps/pensyve/llms.txt
local use - **Scales to cloud**: Postgres backend, managed service at pensyve.com ## Integration Options ### MCP Server (Antigravity CLI, Claude Code, Cursor, Cline, Windsurf, Continue, VS Code Copilot) The MCP server exposes
stabganllms.txtstabgan/openrouter-mcp-multimodal/llms.txt
stabgan/openrouter-mcp-multimodal (v5.0.1) > MCP server — 19 tools, 300+ OpenRouter models. Text chat, vision/audio/video analysis, image/audio/video generation, model catalog, rerank, health check. Node.js 22+ (Docker uses Node 24). Get a free
arthjeanllms.txtarthjean/paneflow/llms.txt
blocking JSON-RPC client used by CLI and MCP. - [MCP crate](crates/paneflow-mcp/) - read-only MCP server implementation. - [MCP install crate](crates/paneflow-mcp-install/) - per-agent MCP config installer. - [Shim crate](crates/paneflow-shim/) - helper
guardanallms.txtguardana/guardana/site/llms.txt
source AI security verification. Its rule engine scans model artifacts, probes live endpoints and MCP servers, and grades completed agent runs. Use it on a laptop, in CI, or beside
MikkoParkkolallms.txtMikkoParkkola/trvl/llms.txt
trvl > AI travel MCP server and CLI for Google Flights, Google Hotels, Booking.com, Trivago, Airbnb, Hostelworld, HomeToGo, trains, buses, ferries, door-to-door multimodal itineraries, price alerts, award travel
AWSllms.txtaws/tools-for-devops-agent/llms.txt
response, root cause analysis, and operational troubleshooting. This repository contains skills, custom agents, and MCP servers that can be used with AWS DevOps Agent, as well as templates for writing
jangtrinhllms.txtjangtrinh/design-os-3d-blender/docs/llms.txt
scripts, accompanied by evidence-graded reviews in interactive Three.js 3D viewers. ## Model Context Protocol (MCP) Server `design-os-3d-blender` exposes a certified First-Party Model Context Protocol server
G12789llms.txtG12789/mcp-quickstart/llms.txt
mcp-quickstart > A CLI that scaffolds a working, testable, publishable Model Context Protocol (MCP) server in one command. TypeScript or Python, with example tool/resource/prompt, MCP Inspector wiring, and passing unit
krzkollms.txtkrzko/google-cloud-mcp/llms-full.txt
Each client may support different MCP features, allowing for varying levels of integration with MCP servers. ## Feature support matrix {/* prettier-ignore-start */} | Client | [Resources] | [Prompts] | [Tools] | [Discovery] | [Sampling] | [Roots] | [Elicitation
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.
