How real projects summarise themselves for language models.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
karanb192llms.txtkaranb192/awesome-claude-code-mods/docs/llms.txt
evaluating DeepSeek-backed workflows within the ruflo swarm. - [ruflo-docs](https://github.com/ruvnet/ruflo/tree/main/plugins/ruflo-docs): Documentation generation, API docs (JSDoc/TSDoc/OpenAPI), and drift detection: drives the `document` background worker via hooks_worker-dispatch
heyderekjllms.txtheyderekj/dinky/site/llms.txt
application/json`, browser `Origin` requests are refused). Same JSON contract for `--json` and `POST /v1/compress`. Documented in-repo: `docs/local-cli.md` (schema `dinky.image.compress/1.0.0`). **No** upload to dinkyfiles.com; paths are explicit
Kevin-Liu-01llms.txtKevin-Liu-01/Claude-of-Tanks/public/llms-full.txt
reference > Canonical, agent-readable reference for the public Claude of Tanks product and technical documentation. Last reviewed 2026-09-30. Canonical site: https://cot.kevinliu.studio/. Creator: Kevin
Kevin-Liu-01llms.txtKevin-Liu-01/Claude-of-Tanks/public/llms.txt
account required. Use the official pages below as the primary public sources. Current runtime documentation outranks old screenshots, historical release notes, and third-party descriptions. Vehicle and armor data describe
smartcontractkitllms.txtsmartcontractkit/documentation/public/llms.txt
Chainlink Documentation > Navigation index for Chainlink developer documentation. Use this file to locate the most relevant page for a task. Prefer `.md` pages. Retrieve the smallest relevant page first
erikdarlingdatallms.txterikdarlingdata/PerformanceMonitor/llms.txt
data to Claude Code, Cursor, and other LLM clients - 15,000+ downloads across releases ## Documentation - [README](https://github.com/erikdarlingdata/PerformanceMonitor/blob/main/README.md): Overview, quick start for Lite and Darling, and links
razzantllms.txtrazzant/claudexor/site/llms.txt
uses bounded Claudexor context packets, not transfer of a vendor-native session between credentials. ## Documentation - [README and quickstart](https://github.com/razzant/claudexor#readme) - [Credential profiles and quota](https://github.com/razzant/claudexor#credential-profiles-and-quota) - [Integrations
EliaAlbertillms.txtEliaAlberti/cpr-compress-preserve-resume/llms.txt
logs to other folders and mirrors them. - The transcript format Claude Code writes is documented as internal; the parser is defensive and the curated summary never depends on it. - Tests
Azure-SamplesReads credentialsllms.txtAzure-Samples/azure-ai-travel-agents/llms.txt
containing specifically included files and files not matching ignore patterns, combined into a single document by Repomix. # File Summary ## Purpose This file contains a packed representation of a subset
cristicretuReads credentialsllms.txtcristicretu/diri/website/llms-full.txt
Diri documentation --- Source: https://diri.sh/docs/ # Diri documentation > How to install diri, run coding agents side by side, keep their work apart, review it, and let agents start and coordinate
cristicretullms.txtcristicretu/diri/website/llms.txt
read-only docs MCP server is at https://diri.sh/mcp. ## Getting started - [Diri documentation](https://diri.sh/docs/index.md): How to install diri, run coding agents side by side, keep their work
juyterman1000llms.txtjuyterman1000/entroly/docs/llms-full.txt
Entroly Extended Documentation Index > Entroly is an open-source, local-first Verified Code Intelligence + Context Assurance system for AI agents. It combines parser-backed repository understanding, budgeted evidence selection, recoverable
juyterman1000llms.txtjuyterman1000/entroly/docs/llms.txt
Agents, CrewAI, AutoGen, Claude Code enterprise-provider routes, VS Code Copilot, and Grok are documented with explicit guided or provider-routing boundaries rather than advertised as dedicated adapters. Verified matrix
NSHipsterllms.txtNSHipster/sosumi.ai/public/llms.txt
browser and refresh the page to view its content. This service translates Apple Developer documentation, Human Interface Guidelines, WWDC sessions, and external Swift-DocC sites into AI-friendly Markdown. Access
duyunzhoudyzllms.txtduyunzhoudyz/gongwen-skills/llms.txt
gongwen-skills > AI Agent Skills for writing Chinese official documents (公文). 22 skills covering drafting, revision, review, and GB/T 9704 standard Word layout. Supports Claude Code, Codex, Cursor, Gemini
Consensysllms.txtConsensys/doc.linea/static/llms.txt
Linea Documentation > These docs are the canonical public reference for Linea Mainnet, Linea > Sepolia, Linea developer APIs, and Lineth, the open-source rollup stack and > protocol that powers Linea
HeiGeAillms.txtHeiGeAi/heige-codex-skin-studio/llms-full.txt
theme; a top menu switches themes instantly and controls next-launch persistence. Full English documentation: [README.en.md](README.en.md). ## 作者与同系项目 由 [问问黑哥（HeiGeAi）](https://github.com/HeiGeAi) 打造。公众号「问问黑哥」写 AI 落地深度文章
liliang-cnReads credentialsllms.txtliliang-cn/cortexdb/docs/llms-full.txt
CortexDB — full documentation > Generated from README.md and docs/GUIDE.md at commit 63e97a9. Summary: https://liliang-cn.github.io/cortexdb/llms.txt # CortexDB [](https://pkg.go.dev/github.com/liliang-cn/cortexdb/v2) [](https://github.com/liliang-cn/cortexdb/actions/workflows/ci.yml) [](https://codecov.io/gh/liliang-cn/cortexdb)
liliang-cnllms.txtliliang-cn/cortexdb/docs/llms.txt
Website](https://liliang-cn.github.io/cortexdb/): overview, quick start, benchmarks, FAQ ([中文](https://liliang-cn.github.io/cortexdb/zh/)) - [Full documentation as one text file](https://liliang-cn.github.io/cortexdb/llms-full.txt): README and the complete guide - [README](https://github.com
violit-devReads credentialsllms.txtviolit-dev/violit/doc/llms.txt
info`, `callout_warning`, `callout_success`, etc.) are the preferred way to generate admonition-style documentation UI. --- ## 8. Chat Interface ```python from typing import Any, cast messages = app.state([ {"role": "assistant", "content
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.
