How real projects summarise themselves for language models.
retracesoftwarellms.txtretracesoftware/retracesoftware/llms.txt
replaying it locally. ## Future Work Retrace includes early agent-facing commands and an MCP server for inspecting recordings. Useful entry points include: - `retrace agent-context --recording ` - `retrace diagnose --recording ` - `retrace
surendranbllms.txtsurendranb/google-search-console-mcp/llms.txt
Google Search Console (GSC) MCP Server > Model Context Protocol (MCP) server for Google Search Console organic search analytics, keyword positions, URL inspection, and sitemaps. ## Installation - UVX: `uvx google-search-console
The-Best-Codesllms.txtThe-Best-Codes/agent-one/.agents/docs/modelcontextprotocol.io/llms-full.txt
modelcontextprotocol.io/docs/2026-07-28/develop/build-client Get started building your own client that can integrate with all MCP servers. In this tutorial, you'll learn how to build an LLM-powered chatbot client that
The-Best-Codesllms.txtThe-Best-Codes/agent-one/.agents/docs/modelcontextprotocol.io/llms.txt
Model Context Protocol (MCP)?](https://modelcontextprotocol.io/docs/2026-07-28/getting-started/intro.md) - [Architecture overview](https://modelcontextprotocol.io/docs/2026-07-28/learn/architecture.md) - [Understanding MCP servers](https://modelcontextprotocol.io/docs/2026-07-28/learn/server-concepts.md) - [Understanding MCP clients](https://modelcontextprotocol.io/docs/2026-07-28/learn/client-concepts.md) - [Versioning](https://modelcontextprotocol.io/docs/2026-07-28/learn/versioning.md) - [Connect
MonadWorksllms.txtMonadWorks/agentify/llms.txt
Agentify transforms OpenAPI specifications into agent interface formats with a single command. Currently generates MCP Servers with security scanning; additional formats are planned. ## Quick Start ```bash npx agentify-cli transform
NickCrewllms.txtNickCrew/Claude-Cortex/site/llms-full.txt
Python CLI plus Textual TUI. It bundles curated agents, skills, rules, hooks, and MCP server definitions for Claude Code, and enforces quality gates — independent code review, test-coverage audits, lint
NickCrewllms.txtNickCrew/Claude-Cortex/site/llms.txt
behavioral rules cortex hooks list|install install and validate hooks cortex mcp list|diagnose MCP server discovery and diagnostics cortex ai recommend|watch skill recommendations (one-shot or daemon) cortex
nirholasllms.txtnirholas/UCAI/llms-full.txt
Interface (UCAI) 🔗 ABI to MCP | The open standard for connecting AI agents to blockchain. MCP server generator for smart contracts. Claude + Uniswap, Aave, ERC20, NFTs, DeFi. Python CLI, Web3 integration
nirholasllms.txtnirholas/UCAI/llms.txt
Contract Tools > Turn any smart contract into Claude tools. The easiest way to build MCP servers from Ethereum ABIs. ## What is UCAI? UCAI (Universal Chain AI) connects AI assistants like
plasmate-labsllms.txtplasmate-labs/plasmate/website/llms.txt
interactive elements, stable references, actions, and content. It runs as a CLI, daemon, native MCP server, AWP server, and CDP compatibility server. ## Release status - Latest published Rust engine: v0.5.1. - Next
qormllms.txtqorm/platform/llms.txt
with rollback, packages as web / iOS / Android / > desktop, and exposes to AI agents over MCP. No cgo — it cross-compiles > everywhere. Dual-consumer by design: every artifact is readable, installable
ZeroPointRepollms.txtZeroPointRepo/awesome-grok-bot/llms.txt
Grok Bot skills, plugins, and MCP servers > Curated directory of skills, plugins, MCP servers and self-hosted alternatives for Grok Bot, the always-on AI teammate from xAI/SpaceXAI and Cursor
couchbasellms.txtcouchbase/mcp-server-couchbase/llms.txt
Couchbase MCP Server > Couchbase MCP Server is a self-hosted Model Context Protocol (MCP) server that lets AI agents and LLM-powered assistants (Claude, Cursor, Windsurf, VS Code Copilot, JetBrains
fluttersdkllms.txtfluttersdk/wind/llms.txt
WindSlotRecipe` variant composition, server-driven UI via `WDynamic`, and three AI integration layers (hosted MCP server, Claude Code skill, and a skill distributed to 8+ AI clients via fluttersdk/ai). Open
littlebearappsllms.txtlittlebearapps/outlook-assistant/llms.txt
flow (default) — no auth server, no port forwarding, no SSH tunnels. State persists across MCP server restarts. Works from Untether, mosh, SSH, and headless environments. - **Email forensics**: Built-in header
Nagarjuna2997llms.txtNagarjuna2997/ios-agent-skill/site/llms-full.txt
checks Decision checkpoints Situation Action or status Evidence or boundaryLocal coding client Local stdio MCP server Node.js; Xcode for simulator workBrowser conversation Supported remote connection or portable guidance Account policy
Nagarjuna2997llms.txtNagarjuna2997/ios-agent-skill/site/llms.txt
WidgetKit](https://nagarjuna2997.github.io/ios-agent-skill/guides/frameworks-widgetkit.html) - [MCP Usage Examples](https://nagarjuna2997.github.io/ios-agent-skill/guides/mcp-examples.html) - [Installing the iOS Agent MCP Server](https://nagarjuna2997.github.io/ios-agent-skill/guides/mcp-installation.html) - [Apple Knowledge MCP](https://nagarjuna2997.github.io/ios-agent-skill/guides/mcp-knowledge-server.html) - [Official MCP Registry publication
curie-engllms.txtcurie-eng/curie/llms.txt
examples/text-stats-engine/README.md](examples/text-stats-engine/README.md): a bundle that ships its own tools as an in-bundle stdio MCP server, a shape a hosted harness cannot do. ## Optional - [SECURITY.md](SECURITY.md): the security posture
gvaibhavllms.txtgvaibhav/TAM-MCP-Server/llms.txt
MCP-Server Agentic Application - LLM Development Guide ## Project Objective Build a sophisticated multi-agent system for Total Addressable Market (TAM) analysis using a pure Model Context Protocol (MCP) ecosystem
netkrllms.txtnetkr/mini-hids/llms.txt
roots for suspicious script patterns, stores ban state in SQLite, and exposes an MCP tool server for agent-native security operations. Mini-HIDS is optimized for local or single-host
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.
