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.
garrytanReads credentialsllms.txtgarrytan/gbrain/llms.txt
configuration facts. - [Harness validation evidence](https://raw.githubusercontent.com/garrytan/gbrain/master/docs/guides/harness-validation.md): Local lifecycle and HTTP/worker proof, reproducible tests, and the remaining actual-harness acceptance checks. ## Core entry points - [AGENTS.md](https://raw.githubusercontent.com/garrytan/gbrain/master/AGENTS.md): Start
Steady43 mentions in 2 weeks
No other project uses it yet
OpenAIllms.txtopenai/openai-agents-python/docs/llms-full.txt
openai.github.io/openai-agents-python/visualization/): Demonstrates embeddable visualizations for session timelines, message flows, and tool interactions. - [Testing](https://openai.github.io/openai-agents-python/testing/): Build deterministic, provider-neutral tests for Agent, Sandbox, Realtime, and Voice workflows. ## Coordination
No other project uses it yet
OpenAIllms.txtopenai/openai-agents-python/docs/llms.txt
openai.github.io/openai-agents-python/context/): Control what past messages, attachments, and tool runs are injected into prompts. - [Testing](https://openai.github.io/openai-agents-python/testing/): Test Agent, Sandbox, Realtime, and Voice workflows deterministically without provider requests. ## Coordination
No other project uses it yet
foundationllms.txtfoundation/foundation-sites/docs/llms-full.txt
# Yeti 7.0.0-alpha.2 Yeti is a plain-CSS framework. Three rules cover every component
No other project uses it yet
alirezarezvanillms.txtalirezarezvani/claude-skills/docs/llms-full.txt
repo deliberately avoids - Dependencies between skills (each stays self-contained) - Complex build systems or test frameworks (portability first) - Generic advice instead of specific frameworks - LLM calls in scripts (defeats portability
Steady31 mentions in 2 weeks
No other project uses it yet
OthmanAdillms.txtOthmanAdi/planning-with-files/llms.txt
pass rate with the skill vs 6.7% without in the formal eval; a 1084-test suite guards the mechanisms. - Differentiators: an opt-in completion gate, multi-agent shared state
Steady14 mentions in 2 weeks
No other project uses it yet
enescingozllms.txtenescingoz/awesome-n8n-templates/llms.txt
case (AI/LLM integration, email automation, social media, HR, DevOps, document processing). Review, configure, and test each workflow before use. Created by Enes Cingoz. ## What is this repository? Awesome n8n Templates
No other project uses it yet
NirDiamantllms.txtNirDiamant/GenAI_Agents/llms.txt
Evaluation](https://github.com/NirDiamant/GenAI_Agents/blob/main/all_agents_tutorials/trace_based_agent_evaluation.ipynb): Evaluate an agent from its execution traces. - [End-to-End Testing Agent](https://github.com/NirDiamant/GenAI_Agents/blob/main/all_agents_tutorials/e2e_testing_agent.ipynb): An agent that writes and runs end-to-end tests. - [Human
No other project uses it yet
Evil0ctalllms.txtEvil0ctal/Douyin_TikTok_Download_API/llms.txt
console, > backed by an identity pool (cookies + proxies + fingerprints) that mints, > tests, cools and retires its own identities. Open source (Apache-2.0), free, > and it runs entirely on your
No other project uses it yet
DuarteSantos8Reads credentialsllms.txtDuarteSantos8/openGym/website/llms.txt
built - Developed with Claude Code (Anthropic's coding agent); changes are reviewed, tested and released by the maintainer. The app itself needs no AI service; the AI coach
No other project uses it yet
xerj-orgPipes a download into a shellllms.txtxerj-org/xerj/landing/llms-full.txt
query and aggregation type, generated from the engine's own dispatch tables and unit-tested against them 7. ENDPOINT CATALOGUE ....... the complete Elasticsearch-compatible surface on :9200 8. MINIMAL
Steady34 mentions in 2 weeks
No other project uses it yet
xerj-orgPipes a download into a shellllms.txtxerj-org/xerj/landing/llms.txt
trained for), the shipped model scores 90.29 where Opus 5.5 scores 100: not a test on unseen questions, and not a claim of general question answering. > - **Not implemented
Steady34 mentions in 2 weeks
No other project uses it yet
emcie-collms.txtemcie-co/parlant/llms.txt
Parlant to your business: it writes the policies, connects your systems, and runs the tests. Parlant provides the rest: an engine that follows your policies in every conversation, checks
No other project uses it yet
Vincentwei1021llms.txtVincentwei1021/video-shotcraft/gallery/llms.txt
gauge-readout-moves](https://vincentwei1021.github.io/video-shotcraft/#gauge-readout-moves): Two instrument reads: a full-range needle self-test and a moving scale that races beneath a fixed pointer. - [scroll-brake-moves](https://vincentwei1021.github.io
Steady2 mentions in 2 weeks
No other project uses it yet
benbjohnsonllms.txtbenbjohnson/litestream/llms.txt
Evidence of problem (logs, file patterns) - [ ] Clear scope (what PR does/doesn't do) - [ ] Runnable test commands - [ ] Race detector tested (`go test -race`) ## Documentation | Document | Purpose | |----------|---------| | [AGENTS.md](AGENTS.md) | Project overview, critical
No other project uses it yet
cactus-computeReads credentialsllms.txtcactus-compute/cactus/llms.txt
base, merged at export, 4-bit. Data is three JSONL files, training, validation and test, one clip per line, the audio path relative to the file; a `language` outside
No other project uses it yet
cactus-computeReads credentialsllms.txtcactus-compute/needle/llms.txt
base, merged at export, 4-bit. Data is three JSONL files, training, validation and test, one clip per line, the audio path relative to the file; a `language` outside
No other project uses it yet
tonhowtfReads credentialsllms.txttonhowtf/omniget/llms-full.txt
Code, Codex, Gemini CLI and Ollama Claude Code, run through OmniGet, fixes a failing test in about 15 seconds from one command. It asks permission with the diff on screen
No other project uses it yet
tonhowtfllms.txttonhowtf/omniget/llms.txt
Ollama models, with per-folder permissions, undo, durable jobs, loops that repeat until a test command passes, an embedded MCP server with 49 tools, and an isometric house called
No other project uses it yet
NangoHQReads credentialsllms.txtNangoHQ/nango/docs/llms-full.txt
customize behavior per customer while keeping the implementation in code you can review, test, and version control. ## How it works Embed Nango Auth in your product so users can connect
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.
