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.
griddynamicsPipes a download into a shellllms.txtgriddynamics/rosetta/llms-full.txt
questions, never stop once coding. Rosetta: approval gates after specs/plans, before risky actions, before tests continue; batch 5–10 questions, prioritized by impact, 1 decision/question; stop+ask vs guess
oxbshwllms.txtoxbshw/watch-skill/llms.txt
variables - [Agent matrix](https://github.com/oxbshw/watch-skill/blob/main/docs/agents/README.md): per-client setup and what has been machine-tested - [Architecture](https://github.com/oxbshw/watch-skill/blob/main/docs/architecture.md): data model, provider boundaries, extension points - [THE LOOP](https://github.com/oxbshw/watch-skill/blob/main/docs/guides/the-loop.md):
Google Cloudllms.txtGoogleCloudPlatform/cluster-toolkit/llms-full.txt
source /usr/lib/openfoam/openfoam${vars.openfoam_image_tag}/etc/bashrc && exec \"$@\""), openfoam]`, `openfoam_image_tag=2406`, `openfoam_smoke_test_runners=[{content: $("#!/bin/bash\nset -euo...`, `openfoam_upstream_image=opencfd/openfoam-default`, `prereq_runners=[{content: #!/bin/bash
Google Cloudllms.txtGoogleCloudPlatform/cluster-toolkit/llms.txt
github.com/GoogleCloudPlatform/cluster-toolkit.git cd cluster-toolkit make ./gcluster --version ``` ## CLI Discovery & Workflow Commands Always run `test -x ./gcluster || make` at the repository root before invoking `./gcluster` in a source checkout: - **List
yologdevllms.txtyologdev/yoagent/llms.txt
docs/concepts/callbacks.md): the older hooks - [Decision models](docs/concepts/decision-models.md): typed judgments, tool gate, input guard ## Guides - [Testing your agent](docs/guides/testing.md): MockProvider - [MCP](docs/guides/mcp.md) · [OpenAPI](docs/guides/openapi.md) - [WebAssembly and Cloudflare Workers](docs/guides/wasm-workers.md) ## Reference
SentryReads credentialsllms.txtgetsentry/vitest-evals/packages/docs/public/llms.txt
vitest-evals > Harness-backed AI evaluation tests on top of Vitest. `vitest-evals` lets teams write evals as ordinary Vitest tests while still capturing the AI-specific data needed
mindroom-aiReads credentialsllms.txtmindroom-ai/mindroom/skills/mindroom-docs/references/llms-full.txt
forces' BwMessenger, Germany's national healthcare messenger TI-Messenger, and a messenger NATO is testing all run on it. The [Security Model](https://docs.mindroom.chat/architecture/security-posture/) documents exactly which boundary protects
OpusGameLabsllms.txtOpusGameLabs/game-creator/skills/threejs-game/reference/llms-full.txt
# Three.js > Three.js is a cross-browser JavaScript library for creating 3D graphics using WebGL
mediar-aillms.txtmediar-ai/mcp-server-macos-use/llms.txt
macOS apps that have no CLI or API (Finder, System Settings, App Store) - GUI testing and verification (navigate to a screen, check element state) - Multi-app workflows (open
scversellms.txtscverse/pertpy/docs/llms.txt
scores in pooled CRISPR screens. - [Differential abundance without labeled groups](https://pertpy.scverse.org/page/api/tools_index.html#compositional-analysis): `pt.tl.Milo` tests differential abundance on k-nearest-neighbor graph neighborhoods. - [Compositional analysis with labeled groups](https://pertpy.scverse.org
Mina-Massoudllms.txtMina-Massoud/Mina-Rich-Editor/public/llms.txt
45KB gzipped. ## Key Facts - License: MIT (free for commercial use) - Bundle size: ~45KB gzipped - Test coverage: 440+ tests - Block types: 15+ (paragraphs, headings, lists, code, tables, images, toggles, etc.) - Framework
LangChainReads credentialsllms.txtlangchain-ai/langchain-aws/llms-full.txt
response = secure_llm.secure_invoke("Tell me about data privacy laws") ``` ## Testing and Monitoring ### Integration Testing ```python import pytest from unittest.mock import patch, MagicMock from langchain_aws import ChatBedrock, BedrockEmbeddings class TestLangChainAWS
zenodollms.txtzenodo/zenodo-rdm/static/llms.txt
with AI tools or agents: - Publishing a record is public and registers a DOI. Test on the [sandbox](https://sandbox.zenodo.org), which needs its own account and token (see [testing
Kooboollms.txtKooboo/Kooboo/llms.txt
Utils: 3 functions - Settings: 2 functions ## Optional - [5000 sites benchmark](https://github.com/Kooboo/Kooboo/blob/main/Docs/5000-sites-benchmark.md): stress-test evidence for running thousands of dynamic sites on one instance. - [Under 1 ms render benchmark
baseReads credentialsllms.txtbase/docs/docs/llms-full.txt
docs.base.org/base-chain/network-information/ecosystem-bridges) for routes from Ethereum, Solana, and Bitcoin. ## Testnet (Base Sepolia) - Get free test ETH and USDC from the [Base faucets](https://docs.base.org/base-chain/network-information/network-faucets). - Test USDC is also available
basellms.txtbase/docs/docs/llms.txt
outcome: integrate DeFi, tokenize assets, issue stablecoins, accept payments, or run private transactions. - [Test on Vibenet](https://docs.base.org/build-on-base/test-on-vibenet): Build and test against Base's newest chain-level features
Orkas-AIllms.txtOrkas-AI/Orkas-VideoStudio/llms.txt
choose a framework, SaaS editor or this project. - [Development](https://github.com/Orkas-AI/Orkas-VideoStudio/blob/main/README.md#development): Deterministic video tests, the e2e production run, the pnpm verify gate before commits, artifact retention and the zero
el09xccxy-stackllms.txtel09xccxy-stack/oss-investment-scorecard/llms.txt
projects from Seed through Series B. They have not yet been back-tested against funding or exit outcomes; v2.0 will do that. From v1.4 (October 2026), the primary audience
raysonmengPipes a download into a shellllms.txtraysonmeng/agent-bridge/site/llms.txt
Linux (Windows not officially supported yet) - Runtime: Bun (required — Node.js alone is not sufficient) - Tests: 1,700+ - Runs 100% locally; no accounts, API keys, or servers needed for AgentBridge itself
caiopizzolReads credentialsllms.txtcaiopizzol/cnpj-data-pipeline/llms.txt
just down just db just run just reset just lint just format just test just check ``` Use uv and just as the primary flow. Do not replace them with
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.
