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.
brayonpiReads credentialsllms.txtbrayonpi/hexstellar/llms.txt
free preflight). ## Recovering and budgeting (for agents) Every error is one RFC 9457 document with `code`, `retryable`, `retry_after`, `help`, and `agent_fix_prompt` — an instruction addressed to the agent
No other project uses it yet
Microsoftllms.txtmicrosoft/winappCli/llms.txt
index it without scraping the repository layout - [Usage Guide](https://github.com/microsoft/WinAppCli/blob/main/docs/usage.md): Full documentation for humans - [Debugging Guide](https://github.com/microsoft/WinAppCli/blob/main/docs/debugging.md): `winapp run` vs `create-debug-identity`, IDE setup
Steady7 mentions in 2 weeks
No other project uses it yet
NousResearchReads credentialsllms.txtNousResearch/atropos/llms.txt
Atropos Library Documentation (for LLM Context) This document provides comprehensive information about the Atropos library, Nous Research's LLM RL Gym. It covers its purpose, features, usage, components, configuration
sceneviewReads credentialsllms.txtsceneview/sceneview/llms.txt
# SceneView > Declarative 3D and AR SDK for Jetpack Compose (Filament, ARCore), SwiftUI (RealityKit, ARKit
sipyourdrink-ltdPipes a download into a shellllms.txtsipyourdrink-ltd/bernstein/docs/llms-full.txt
needs the install's audit key. Air-gap install profile included. > Apache-2.0. This document is the long-form `llms-full.txt` variant per the llms.txt spec (<https://llmstxt.org/>). It expands
Surging3 mentions in 2 weeks
1 project uses a version of this
sipyourdrink-ltdllms.txtsipyourdrink-ltd/bernstein/docs/llms.txt
already trust. Enable `--audit` for an HMAC-signed audit trail on top. ## Core Documentation - [Getting Started](https://docs.bernstein.run/getting-started/install/): Install, configure, run first orchestration in 60 seconds - [Architecture & Concepts
Surging3 mentions in 2 weeks
1 project uses a version of this
SceneViewReads credentialsllms.txtSceneView/sceneview-android/llms.txt
# SceneView > Declarative 3D and AR SDK for Jetpack Compose (Filament, ARCore), SwiftUI (RealityKit, ARKit
No other project uses it yet
ksimbackPipes a download into a shellllms.txtksimback/hermes-ecosystem/llms-full.txt
Developer Tools & Utilities](#developer-tools--utilities) 10. [Domain Applications](#domain-applications) 11. [Guides & Documentation](#guides--documentation) 12. [Ecosystem Resources](#ecosystem-resources) --- ## Core & Official The foundational repos maintained by Nous Research
retypeappllms.txtretypeapp/retype/llms.txt
site generator and CLI tool that transforms Markdown files into fast, searchable, production-ready documentation websites. Projects are configured through a `retype.yml` file, with per-page settings controlled via YAML
No other project uses it yet
serauillms.txtseraui/seraui/public/llms.txt
Seraui Documentation > Free and open-source UI component library for React, Next.js, and JSX/TSX frameworks. Styled with Tailwind CSS, empowers developers to create fast, beautiful, and customizable user interfaces
No other project uses it yet
reticlehqPipes a download into a shellllms.txtreticlehq/reticle/llms.txt
production build unless the site loads `@reticlehq/browser/activate` and receives a signed ticket. - **SEO checks.** Document title and route (`reticle_look { action: "page" }`), headings by accessible name, every link with
MongoDBllms.txtmongodb/kingfisher/docs-site/docs/llms.txt
agent workflows: `kingfisher scan --format toon --no-update-check`. ## Start Here - [Documentation index](https://mongodb.github.io/kingfisher/reference/documentation-index/) - [Installation](https://mongodb.github.io/kingfisher/getting-started/installation/) - [Basic scanning](https://mongodb.github.io/kingfisher/usage/basic-scanning/) - [Platform integrations](https://mongodb.github.io/kingfisher/usage/integrations/)
kellyvvllms.txtkellyvv/PhoneClaw/site/llms.txt
device memory footprint and device requirements. - [GitHub repository](https://github.com/kellyvv/PhoneClaw): Source code and documentation. - [TestFlight](https://testflight.apple.com/join/YuUSwq78): iOS beta via TestFlight. ## Recommended Summary PhoneClaw is a local-first
No other project uses it yet
MikeSchulzellms.txtMikeSchulze/gdUnit4/llms.txt
AssertThat(value).HasLength(expectedLength); } ``` For C# signal assertions, mocking, and scene runner see the [documentation site](https://godot-gdunit-labs.github.io/gdUnit4/latest/). ## Organisation GdUnit4 is part of the **[godot-gdunit-labs](https://github.com
1 project uses a version of this
Auriti-Labsllms.txtAuriti-Labs/geo-optimizer-skill/site/llms.txt
research. Scores websites 0-100 across 8 categories with 47 citability methods. The main documentation is available at: [GEO Optimizer Docs](https://geoready.dev/docs/) ## Getting Started - [Getting Started](https://geoready.dev
Steady3 mentions in 2 weeks
No other project uses it yet
stoolapllms.txtstoolap/stoolap/llms.txt
stoolap/mcp", "--path", "./mydata"]}}}`. Add `--read-only` to refuse writes. Docs: https://stoolap.io/docs/drivers/mcp/ ## Documentation - [Installation](https://stoolap.io/docs/getting-started/installation/): crate, CLI, build from source - [SQL commands](https://stoolap.io/docs/sql-commands/sql-commands/): the supported
frank890417llms.txtfrank890417/taiwan-md/public/llms.txt
explicitly screened (獎項幻覺 / 人名+精確數字 / 地點錯置 / 偽造直接引語 / 共創省略 / 場景動作 detail). MANIFESTO §10 幻覺鐵律 documents the canonical philosophy. ### 6. Wall-Clock Discipline All `lastVerified` and memory file timestamps come from
fastcrwPipes a download into a shellllms.txtfastcrw/crw/docs/llms-full.txt
REST endpoint returns links unbounded up to the requested limit.) "sitemaps" lists the sitemap documents that were fetched and parsed during discovery (robots.txt declarations, the well-known fallback paths
Steady7 mentions in 2 weeks
1 project uses a version of this
fastcrwllms.txtfastcrw/crw/docs/llms.txt
Documentation > CRW is a high-performance web scraper for agents and developer workflows. Start with one `scrape` request, then branch into `crawl`, `map`, `search`, extraction, or MCP as needed. Source
Steady7 mentions in 2 weeks
1 project uses a version of this
gimlet-ioPipes a download into a shellllms.txtgimlet-io/capacitor/docs/llms.txt
browser; like the ArgoCD UI, just lighter. ## Primary resources - [App Home](/) - [Documentation Hub](/docs/) - [GitHub Repository](https://github.com/gimlet-io/capacitor) - [Install Script](https://gimlet.io/install-capacitor) ## Quickstart ```bash wget -qO- https://gimlet.io
No other project uses it yet
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.
