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.
RyanAlbertsllms.txtRyanAlberts/best-of-Agent-Harnesses/llms.txt
order. Each one eliminates most of the list; by the en - How to test-drive a harness: https://ryanalberts.github.io/best-of-Agent-Harnesses/compare/how-to-test-drive-a-harness/ — Spec sheets cannot answer "which harness should I use," because
koxudaxiPipes a download into a shellllms.txtkoxudaxi/fastapi-code-generator/docs/llms-full.txt
input api.yaml --output app --output-model-type pydantic_v2.BaseModel ``` For the full option matrix and tested examples, see the [CLI reference](cli-reference.md). ## CLI Help Snapshot This block is generated from
brayonpiReads credentialsllms.txtbrayonpi/hexstellar/llms.txt
units and re-run the DOMAIN check yourself. **`hexstellar demo` is a smoke test — it proves the pipe, never the product. The live catalogue contains encoding recipes, not the allowed
No other project uses it yet
NousResearchReads credentialsllms.txtNousResearch/atropos/llms.txt
github.com/NousResearch/atropos.git cd atropos # Core usage from local clone pip install -e . # Development (includes testing, linting tools) pip install -e .[dev] # Running examples (includes dependencies like vLLM, transformers) pip install
SceneViewReads credentialsllms.txtSceneView/sceneview-android/llms.txt
Compose fit together - [Performance](https://sceneview.github.io/docs/performance/): frame budget, quality levels, what costs what - [Testing](https://sceneview.github.io/docs/testing/): testing a scene without a device - [Integrations](https://sceneview.github.io/docs/integrations/): Sketchfab, Rerun.io
sceneviewReads credentialsllms.txtsceneview/sceneview/llms.txt
Compose fit together - [Performance](https://sceneview.github.io/docs/performance/): frame budget, quality levels, what costs what - [Testing](https://sceneview.github.io/docs/testing/): testing a scene without a device - [Integrations](https://sceneview.github.io/docs/integrations/): Sketchfab, Rerun.io
chernistryPipes a download into a shellllms.txtchernistry/bernstein/docs/llms-full.txt
same run. - Git worktree isolation per agent. Main branch stays clean. - Janitor verification: tests, lint, types, PII gating. - File-based state in `.sdd/`. No database. Inspect with `cat`, back
Surging3 mentions in 2 weeks
1 project uses a version of this
Ataraxy-Labsllms.txtAtaraxy-Labs/weave/docs/llms.txt
wins (git conflicted, weave resolved cleanly) - 0 regressions on C, Python, Go - Repos tested: git/git (C), Flask (Python), CPython (C/Python), Go (Go), TypeScript (TS) Full benchmark suite: 11ms. Individual merges
Steady6 mentions in 2 weeks
No other project uses it yet
ksimbackPipes a download into a shellllms.txtksimback/hermes-ecosystem/llms-full.txt
inside a repo and want the agent to read code, edit code, run tests, commit. It's a coding specialist. - **Pick Cursor** when you want AI completions and fixes inside
ksimbackllms.txtksimback/hermes-ecosystem/llms.txt
verdict per entry. 21 curated entries across 7 use cases. Updated 2026-08-20, tested against Hermes v0.20.4. - [Hermes Skills Hub](https://hermesatlas.com/skills/): Every curated pick, the top pick
LING71671Reads credentialsllms.txtLING71671/open-reverselab/docs/llms-full.txt
ascii=False, indent=2)) ``` ### 5e. 固定验证码（开发/测试模式） ```bash # 尝试测试密钥 sitekey: 6LeIxAcTAAAAAJcZVRqyHh71UMIEGNQ_MXjiZKhI # reCAPTCHA test key # 使用测试 sitekey 时，任何 token="test" 都可通过 ``` ## 方法 6：短信验证码绕过 ```python # 6a. 验证码可枚举
No other project uses it yet
reticlehqPipes a download into a shellllms.txtreticlehq/reticle/llms.txt
context (seeded cookies/storage); several agents share one pooled Chromium. **Pairs well with:** a visual testing tool (pixel diffs), Playwright (sites you don't own, cross-browser matrix), axe (full WCAG
godot-gdunit-labsllms.txtgodot-gdunit-labs/gdUnit4/llms-full.txt
addons/gdUnit4/src/`) - `asserts/` — Fluent assertion implementations per type (Array, String, Signal, Vector, Dictionary, etc.) - `core/` — Test case execution, discovery, events, attributes, versioning - `core/execution/` — Test execution pipeline - `core/discovery/` — Test discovery logic - `core/event
1 project uses a version of this
godot-gdunit-labsllms.txtgodot-gdunit-labs/gdUnit4/llms.txt
GdUnit4 > A Godot 4 embedded unit testing framework (plugin) supporting GDScript and C#. GdUnit4 v7.0.0 — supports Godot 4.7–4.8. C# targets net9.0 (.NET SDK 9.0.308). The framework is self-tested
1 project uses a version of this
BankrBotllms.txtBankrBot/openclaw-skills/defi-native/llms.txt
live-data discipline. MIT licensed. ## Core - [SKILL.md](SKILL.md): prime directives, working loop, orientation, competence test - [README.md](README.md): what this is and how it is organized - [api-routes.json](api-routes.json): question
Steady5 mentions in 2 weeks
1 project uses a version of this
fastcrwllms.txtfastcrw/crw/docs/llms.txt
Hosted API keys and self-hosted Bearer auth - [API Playground](https://raw.githubusercontent.com/fastcrw/crw/main/docs/docs/playground.md): Interactive testing before you write code - [Installation](https://raw.githubusercontent.com/fastcrw/crw/main/docs/docs/installation.md): Package-level install options ## Core APIs - [REST
Steady7 mentions in 2 weeks
1 project uses a version of this
asheshgoplaniPipes a download into a shellllms.txtasheshgoplani/agent-deck/llms-full.txt
skip it with `--skip-tmux-config`. ## Development ```bash make build # Build make test # Test make lint # Lint ``` See [CONTRIBUTING.md](CONTRIBUTING.md) for details. ## Star History If Agent Deck saves you time
openresponsesllms.txtopenresponses/openresponses/public/llms.txt
streaming for real-time output. Parameters may be... - [Compliance](https://www.openresponses.org/compliance): Acceptance tests and validation procedures. Test any API endpoint for Open Responses specification compliance. Configure your connection details
No other project uses it yet
vshulczPipes a download into a shellllms.txtvshulcz/deja-vu/docs/llms.txt
what is a contract and what is not, and how to isolate it in tests - [Benchmarks](https://vshulcz.github.io/deja-vu/guide/benchmarks.html): 88.1% hit@1 on LongMemEval-S (470-question cleaned
Steady30 mentions in 2 weeks
No other project uses it yet
agentbay-aiReads credentialsllms.txtagentbay-ai/wuying-agentbay-sdk/llms-full.txt
cloud environment through a simple API: execute commands, browse the web, automate desktop apps, test mobile UIs, or run code — all in secure, disposable sandboxes. --- ## 🎯 What You Can Do 🌐 Browser
1 project uses a version of this
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.
