How real projects summarise themselves for language models.
odds-apillms.txtodds-api/odds-api/llms.txt
betting odds API for coding agents, with simple REST examples, TypeScript SDK, Python SDK, MCP server, mock mode, arbitrage, positive EV, line movement, and bookmaker comparison. Canonical repo: https://github.com
racciolyllms.txtraccioly/docguard/llms-full.txt
CLIs | | Testing | `node:test` + `node:assert` | Built-in, no test framework dependency | | Docker | `Dockerfile` (MCP server image) | Published to GHCR for stdio MCP use; HTTP transport is also available with
TsukumoHQllms.txtTsukumoHQ/WRAI.TH/llms.txt
chat. Multi-agent orchestration over a > local relay (Go + SQLite FTS5), exposed as an MCP server. Open source (AGPL-3.0). ## What it does - Run a fleet: many agents working
wandercomllms.txtwandercom/kindex/docs/llms-full.txt
graph plus the repository's git-tracked .kin/, exposes it through a CLI and MCP server, and gives agents explicit operating rules for using that graph without waiting
wandercomllms.txtwandercom/kindex/docs/llms.txt
Kindex Kindex is a local-first persistent knowledge graph and MCP server that Claude Code, Codex, Gemini CLI, Google Antigravity, OpenCode, Cursor, and other MCP-capable agents all read
korovin-aa97llms.txtkorovin-aa97/talkthrough-mcp/llms.txt
talkthrough-mcp > Local-first MCP server that turns narrated screen recordings (or any > video/audio file) into agent-ready structured data: timestamped transcript > segments, scene-change keyframes, OCR text, and wall
rsdouglasllms.txtrsdouglas/janee/website/llms.txt
credential scope - **Encrypted key storage**: AES-256-GCM encryption for all stored credentials - **MCP server mode**: Expose tools (`janee_list_services`, `janee_execute`, `janee_exec`) for AI agents - **Docker-ready
AnastasiyaWllms.txtAnastasiyaW/knowledge-space/docs/llms.txt
# Happyin Knowledge Space > A comprehensive technical knowledge base with 1319+ curated articles across 28
infiniVllms.txtinfiniV/ultra-instinct-claude-code/llms.txt
MCP tools (~500 tokens each, always loaded) > long CLAUDE.md > agent descriptions. Keep under 10 MCP servers, 80 total tools. Use ENABLE_TOOL_SEARCH=true for large sets. /context shows what
mikusnuzllms.txtmikusnuz/app-publish-mcp/llms.txt
publish-mcp > MCP server for App Store Connect & Google Play Console — manage app listings, screenshots, releases, reviews & submissions from AI assistants ## Install ```json { "mcpServers": { "app-publish-mcp": { "command": "npx", "args
nicholasglazerllms.txtnicholasglazer/gnosis-mcp/llms-full.txt
Gnosis MCP — Full Reference > Zero-config MCP server that makes your markdown docs searchable by AI agents. > SQLite default, PostgreSQL optional. Works with any MCP client — Claude Code, Claude Desktop
nicholasglazerllms.txtnicholasglazer/gnosis-mcp/llms.txt
Gnosis MCP > Zero-config MCP server that makes your markdown docs searchable by AI agents. > SQLite default, PostgreSQL optional. Works with any MCP client — Claude Code, Claude Desktop, Cursor
redis-developerllms.txtredis-developer/adk-redis/docs/llms.txt
implementations, five > RedisVL-backed search tools, selectable Redis Agent Memory or Agent Memory > Server memory backends, MCP toolsets, and semantic cache providers. For agents using the library, read [AGENTS.md](../AGENTS.md
shaqmughalllms.txtshaqmughal/seekstone/llms.txt
Seekstone > Seekstone is an Obsidian MCP server that connects Claude (and any Model Context Protocol client) to your Obsidian vault. It reads the vault directly from disk — no Obsidian
vishalguptaxllms.txtvishalguptax/claude-code-manager/site/llms.txt
Manager > Free, open-source VS Code extension that puts every Claude Code session, account, MCP server, skill, slash command, hook, and agent into one sidebar. 100% local, zero telemetry. Works
waiaasllms.txtwaiaas/WAIaaS/site/llms.txt
Metaplex) ## Interfaces - **REST API**: OpenAPI-documented HTTP endpoints on localhost (default port 3100) - **MCP Server**: Built-in Model Context Protocol server for direct AI agent integration - **TypeScript SDK**: `@waiaas/sdk
itallstartedwithaideallms.txtitallstartedwithaidea/ContextOS/llms.txt
install contextos updated: 2025-03-09 ## What It Is ContextOS is a single MCP server and CLI that absorbs and extends seven leading open-source AI agent repositories into
JetBrainsllms.txtJetBrains/hexana/docs/llms.txt
editor. The JetBrains plugin additionally ships full WIT language support, an in-process MCP server, Java-side completion (GraalWasm, Chicory), JavaScript / TypeScript type inference (`WebAssembly.instantiate`), Goto-Symbol integration
korniallms.txtkornia/bubbaloop/docs/llms-full.txt
multi-agent Zenoh gateway with per-agent Soul, 4-tier memory, adaptive heartbeat 3. **MCP Server** — 47 tools + agent-internal tools, 3-tier RBAC (Viewer/Operator/Admin), stdio + HTTP 4. **Telemetry Watchdog
michielhdotethllms.txtmichielhdoteth/awesome-ai-agent-tools/llms.txt
Awesome AI Agent Tools > The most comprehensive open-source library for AI agent skills, MCP servers, and agent workflows. 650 installable components across 8 categories -- skills, MCPs, loops, subagents, hooks
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.
