How real projects summarise themselves for language models.
fastagent-shllms.txtfastagent-sh/fastagent/llms.txt
product paths. - [AI-guided start](https://fastagent.sh/start.md): executable instructions for a coding agent. - [Documentation index](https://fastagent.sh/docs/): the full documentation map. ## Guides - [Overview](https://fastagent.sh/docs/overview/): what FastAgent
assaiollms.txtassaio/assaio/site/llms.txt
unmatched` results. Results include method, confidence, provenance, candidates, alternatives and abstention reason; the document stamps the algorithm version. A match uses project and bounded time proximity. It does not establish
openSVMllms.txtopenSVM/solana-mcp-server/llms.txt
Solana MCP Server - LLM Documentation ## Overview The Solana MCP Server provides access to Solana blockchain data through the Model Context Protocol (MCP). It implements comprehensive Solana RPC methods organized into
getaero-iollms.txtgetaero-io/gtm-eng-skills/llms.txt
skills add getaero-io/gtm-eng-skills --all npm install -g @deepline/cli deepline auth login ``` ## Documentation - [Deepline CLI Docs](https://code.deepline.com/docs) - [Deepline AI-Readable Docs](https://docs.code.deepline.com/docs/llms.txt) - [GitHub Repository
hope1026llms.txthope1026/weppy-roblox-mcp/llms-full.txt
publish through this reference. This package intentionally does not ship a standalone full documentation surface. Canonical documentation lives on the web: - Install and setup: https://weppyai.com/en/install - Product documentation
hermes-labs-aillms.txthermes-labs-ai/zer0dex/llms.txt
serving, and querying work together as one persistent memory loop Compatibility: - migration notes precede documented breaking changes during the 0.1.x line - exact CLI behavior: docs/cli.md - exact HTTP behavior: docs/http.md
MishaBear94llms.txtMishaBear94/iso-topology/llms.txt
code tool built agent-first: an LLM can discover the DSL (`isotopo capabilities`), validate documents before render (JSONPath-located issues with fix suggestions; exit codes 0 clean / 2 warnings
sdsrssllms.txtsdsrss/claude-mem-lite/llms.txt
claude-mem / mem0 / MCP reference memory, FAQ - [中文 README](https://github.com/sdsrss/claude-mem-lite/blob/main/README.zh-CN.md): Chinese documentation - [CHANGELOG](https://github.com/sdsrss/claude-mem-lite/blob/main/CHANGELOG.md): version history - [CLAUDE.md](https://github.com/sdsrss/claude-mem-lite/blob/main/CLAUDE.md): architecture map and module roles - [Architecture
Vortx-AIllms.txtVortx-AI/emem/web/llms.txt
cell64, a place name, or lat+lng. Canonical surface: 114 MCP tools, 172 documented /v1 paths, 168 algorithms, 46 declared source schemes (publish-time snapshot; live counts at /v1/agent_card). ## Connect
corezoidllms.txtcorezoid/simulator-ai-plugin/public/llms.txt
intent - **getSkill**: Load a saved skill playbook in full by slug (ref) or id ## Documentation - [Actors](https://raw.githubusercontent.com/corezoid/simulator-ai-plugin/main/plugins/simulator/docs/entities/actors.md): Actor model, fields, status lifecycle - [Forms](https://raw.githubusercontent.com/corezoid/simulator-ai-plugin/main/plugins/simulator/docs/entities/forms.md): Form templates
ohad6kllms.txtohad6k/VibeRaven/llms-full.txt
plan ``` Always use the long flag `--agent-mode`. Do not substitute shorthand aliases in documentation or rules. ## When to run (trigger phrases) Use VibeRaven before launch, deployment, real users, auth
open-agreementsllms.txtopen-agreements/open-agreements/llms-full.txt
Paper, Bonterms, NVCA, YC SAFE) and keep source, license, and validation context with each document. Plain markdown here, machine-readable JSON/CSV twins on openagreements.org. This is legal information, not legal
open-agreementsllms.txtopen-agreements/open-agreements/llms.txt
Paper, Bonterms, NVCA, YC SAFE) and keep source, license, and validation context with each document. Plain markdown here, machine-readable JSON/CSV twins on openagreements.org. This is legal information, not legal
tteonllms.txttteon/seocho/llms.txt
memory. You define a domain > ontology once, then use the same contract to ingest documents, shape graph > writes, generate schema-aware Cypher, and produce answers with traceable > evidence. SEOCHO ships
clawboollms.txtclawboo/clawboo/docs/llms.txt
circuit breakers, and an always-on observability event log. This file indexes the Clawboo documentation for language models. Paths are relative to the documentation root. Documents Clawboo v0.3.1, the current
Goldwaterfungllms.txtGoldwaterfung/Stratawright/llms-full.txt
session control rather than raw OS thread calls or blocking UI events. ## Core Documentation # Quick Start Guide ## 1. Agentic One-Prompt Setup (Recommended) Open your AI agent (**Claude Code**, **Codex
Goldwaterfungllms.txtGoldwaterfung/Stratawright/llms.txt
session control rather than raw OS thread calls or blocking UI events. ## Core Documentation - [Getting Started](QUICKSTART.md): 60-second quickstart guide for building the C++ DAW application and installing agent
johnxiellms.txtjohnxie/awesome-code-docs/llms-full.txt
toeverything/AFFiNE to build, extend, and self-host a modern knowledge workspace combining documents, whiteboards, and databases — powered by BlockSuite, CRDT-based collaboration, and integrated AI copilot features. - Keywords: affine, open
johnxiellms.txtjohnxie/awesome-code-docs/llms.txt
Engineering Plugin Tutorial: Compounding Agent Workflows Across Toolchains: https://github.com/johnxie/awesome-code-docs/tree/main/tutorials/compound-engineering-plugin-tutorial - Context7 Tutorial: Live Documentation Context for Coding Agents: https://github.com/johnxie/awesome-code-docs/tree/main/tutorials/context7-tutorial - Continue Tutorial: Open-Source AI Coding Agents
PavanMudigondallms.txtPavanMudigonda/zero-to-ai/llms-full.txt
production deployment patterns. ### Phase 08 - RAG (Retrieval-Augmented Generation) End-to-end RAG pipelines. Document loading, chunking strategies, retrieval, reranking, generation. Advanced: corrective RAG, self-RAG, multi-step retrieval, graph
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.
