How real projects summarise themselves for language models.
hermes-labs-aillms.txthermes-labs-ai/lintlang/llms-full.txt
keeping the copy with a schema. - H1.4/H1.5/H1.6 compare tools within one container, so two MCP servers may each expose a `search`. A document that is itself one STRONG tool object
Scottcjnllms.txtScottcjn/rustchain-mcp/llms.txt
rustchain-mcp > rustchain-mcp is a Python MCP server that exposes wallet, balance, transfer, bounty, BoTTube, and Beacon tools so AI agents can work with RustChain, earn RTC, publish content
yschimkellms.txtyschimke/compose-ai-tools/site/llms.txt
version-pinned Gradle plugin, a VS Code extension, CI actions, and an optional MCP server and render daemon. Java 17 or newer and Gradle 8.13 or newer are required. ## Getting
ZIZKA-AI-SLllms.txtZIZKA-AI-SL/ZizkaDB/llms.txt
inject relevant memory into future runs. ZizkaDB is open-source (AGPL-3.0, except MCP server which is MIT). It runs as a FastAPI backend + Next.js 14 dashboard on a single
EliasOulkadillms.txtEliasOulkadi/shokunin/llms.txt
/shokunin/): Landing page with overview - [Architecture](docs/ARCHITECTURE.md): System design and component relationships - [MCP API](docs/MCP-API.md): Memory server API documentation - [Changelog](CHANGELOG.md): Version history ## Skill Categories - **Infrastructure**: docker, kubernetes, terraform
EliasOulkadillms.txtEliasOulkadi/shokunin/.pack/llms.txt
with overview - [Architecture](https://github.com/EliasOulkadi/shokunin/blob/main/docs/ARCHITECTURE.md): System design and component relationships - [MCP API](https://github.com/EliasOulkadi/shokunin/blob/main/docs/MCP-API.md): Memory server API documentation - [Changelog](CHANGELOG.md): Version history ## Skill Categories - **Infrastructure**: docker, kubernetes, terraform
jklthinkingllms.txtjklthinking/retinue/docs/llms.txt
Compose hub that listens on port 9219, and exposes coordination to AI agents over MCP (Model Context Protocol) or HTTP with an actor token. Claude Code and Codex runtime exporters
planetabhillms.txtplanetabhi/riseofmachine/public/llms.txt
riseofmachine.com/seo) - [Social](https://riseofmachine.com/social) - [Video](https://riseofmachine.com/video) - [Xtras](https://riseofmachine.com/xtras) ## MCP Servers Model Context Protocol servers from the official registry, grouped by category. - [All MCP Servers
oaslanankallms.txtoaslananka/kicad-mcp-pro/docs/llms.txt
schematic automation, PCB automation, ERC, DRC, DFM, BOM, manufacturing export, live preview, visual evidence, MCP server, Python, PyPI
raphaelmansuyllms.txtraphaelmansuy/adk_training/docs/llms.txt
raphaelmansuy.github.io/adk_training/docs/code_execution)** - Safe code execution environments and sandboxing - **[14: Streaming & SSE](https://raphaelmansuy.github.io/adk_training/docs/streaming_sse)** - Server-sent events and real-time response streaming - **[15: Live API & Audio](https://raphaelmansuy.github.io/adk_training/docs/live_api_audio)** - Real
putervisionllms.txtputervision/state-memory-mcp/docs/llms.txt
Website**: https://statememorymcp.com - **Repository**: https://github.com/putervision/state-memory-mcp - **Description**: Zero-infrastructure, deterministic Model Context Protocol (MCP) server providing AI agents with persistent SQLite state graph memory for tracking tasks, decisions, blockers
Goldziherllms.txtGoldziher/basemind/llms.txt
scriptable CLI, at parity with the MCP tools. - [Installation](https://basemind.ai/start/installation/): Plugin, MCP server, and standalone CLI setup. - [Configuration](https://basemind.ai/reference/configuration/): `.basemind/basemind.toml`, feature flags, and layered overrides. - [Hosted
magnus919llms.txtmagnus919/agent-skills/llms.txt
refactors, output/exit-code debugging, or automation safety. Do not use for GUI/TUI design, conversational tools, MCP server design, or general API architecture; use api-design-and-evolution for the latter. - [cncf
herry2059llms.txtherry2059/project-os-for-codex/public/llms.txt
plus one Git commit. Codex first-run verification: - The project-level configuration requires the MCP server and allowlists exactly the two released tools. - From an installed checkout, `pnpm codex:doctor
UmairBaig8llms.txtUmairBaig8/okf-generator/docs/llms.txt
deterministic extraction via tree-sitter AST parsing, 10 languages, 17 dependency-manifest formats, MCP server included. okf-generator solves the problem of AI agents re-reading entire source files
MarcoPorcellatollms.txtMarcoPorcellato/matryca-plumber/llms.txt
true" } } } } ``` With no CLI subcommand and MCP enabled, `uvx matryca-plumber` starts the **stdio** MCP server. For interactive graph work without MCP, prefer the CLI in section 2.1. #### Hermes Agent
Apra-Labsllms.txtApra-Labs/apra-fleet/llms-full.txt
client](packages/apra-fleet-client/docs/overview.md) | [apra-pm](packages/apra-fleet-se/apra-pm/README.md) | [apra-fleet-mcp](docs/mcp-tools.md) | [Agent Roles](packages/apra-fleet-se/docs/role-contracts.md) ### Fleet Dispatch Topology ```mermaid flowchart LR CP["Control Plane (Server, Engine, Supervisor)"] -->|Dispatch & Sync| M1["MacBook (Claude
Apra-Labsllms.txtApra-Labs/apra-fleet/llms.txt
terminology -- member, task, skill, PM, fleet, doer/reviewer pattern. - [Architecture](docs/architecture.md): How the fleet hub, MCP server, and members interact at a system level. ## Setup - [Install](docs/install.md): Installation, uninstallation
0xzrllms.txt0xzr/freellmpool/docs/llms.txt
quota tracking. > Works as a CLI, a Python library, a local proxy, and an MCP server. Keyless to > start (`pip install freellmpool`); the proxy speaks the OpenAI
dykyi-romanllms.txtdykyi-roman/awesome-claude-code/llms.txt
docs/hooks.md) - PHP 8.4+, PSR-12, readonly classes - DDD/CQRS/Hexagonal patterns - Testing, Documentation generation and audit - MCP servers support (Database, GitHub, etc.) ## Installation ```bash /plugin marketplace add dykyi-roman/awesome-claude-code /plugin install
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.
