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.
agentbay-aiReads credentialsllms.txtagentbay-ai/wuying-agentbay-sdk/llms.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
ClawBiollms.txtClawBio/ClawBio/llms.txt
release: `v0.7.1` - Public framing in `README.md`: `97 skills + 8,182 Galaxy tools + 4,730 tests + benchmark validation` - Catalog status split: `29` MVP skills and `68` planned / legacy skills - Counts above
No other project uses it yet
scrapflyllms.txtscrapfly/scrapfly-scrapers/llms.txt
async functions that return JSON-ready data, with an example script (`run.py`), live tests (`test.py`) and sample output (`results/`). These scrapers are educational examples that accompany the Scrapfly scrape guides
datacontractllms.txtdatacontract/datacontract-cli/llms.txt
ODCS) to lint data contracts, connect to data sources and execute schema and quality tests, and export to different formats. The tool is written in Python and published under
AnswerDotAIllms.txtAnswerDotAI/fastcore/nbs/llms.txt
fastcore's versions of `ThreadPoolExecutor` and `ProcessPoolExecutor` for simpler concurrent processing. - Prefer fastcore's test functions, such as `test_eq`, `test_ne` and `test_close`, for assertions that read clearly
No other project uses it yet
sno-aillms.txtsno-ai/sno-station/llms.txt
guides for the four memory integrations, images, evidence, translations, security page - tests/apps/ — public-contract tests only ## Contributing - CONTRIBUTING.md — DCO sign-off, one change per PR, which checks to run - .github/ISSUE_TEMPLATE
gdsfactoryllms.txtgdsfactory/gdsfactory/docs/llms-full.txt
alternative snake delay - `gf.components.delay_snake_sbend(length=100.0, radius=5.0)` — S-bend delay line ### Test Structures - `gf.components.cutback_bend(component='bend_euler', rows=6, cols=5)` — bend cutback test - `gf.components.cutback_component
No other project uses it yet
hareharePipes a download into a shellllms.txtharehare/mq/docs/llms-full.txt
with many built-in functions and selectors. - **REPL Support**: Interactive command-line REPL for testing and experimenting. - **IDE Support**: VSCode Extension and Language Server Protocol (LSP) support for custom function
No other project uses it yet
TechyCSRllms.txtTechyCSR/OpenCluely/webapp/llms-full.txt
NSIS .exe installer from GitHub Releases. - Linux — .deb installer and AppImage from GitHub Releases. Tested on Ubuntu 20.04+, Debian 11+, Fedora 36+. - macOS 12+ — Not pre-built (Gatekeeper blocks unsigned
No other project uses it yet
adridallms.txtadrida/tracer/llms.txt
separate. CHANGELOG.md distinguishes unreleased source from published packages. ## Install Requires Python 3.12+. CI tests Python 3.12, 3.13, and 3.14. Published package: pip install tracer-llm Current checkout with the unreleased
hanzohanzhellms.txthanzohanzhe/Grandet/llms.txt
install route existing for an app does not mean it has been tested there. Listed prices and supplier statements don't prove model quality or identity. ## Catalogue data - https://github.com
agentic-communityPipes a download into a shellllms.txtagentic-community/mcp-gateway-registry/docs/llms.txt
terraform/` | **Infrastructure as Code** - AWS deployment automation | `aws-ecs/` (ECS Fargate), `modules/` (reusable modules) | | `tests/` | **Test Suite** - pytest unit, integration, E2E tests | `conftest.py`, `unit/`, `integration/` | | `docs/` | **Documentation** - Architecture, guides, design
samueltuyizereReads credentialsllms.txtsamueltuyizere/oc-go-cc/llms.txt
Running ```bash make build # Build binary to bin/routatic-proxy make run # Run without building make test # Run tests with race detector make lint # go vet + test make install # Build and install
borgheiReads credentialsllms.txtborghei/Claude-Skills/site/llms.txt
headcount, hire/contract/defer scenarios, and... - [Internal Comms](https://borghei.github.io/Claude-Skills/skills/business-operations/internal-comms.html): Plan, sequence, and pressure-test internal announcements before they send. Use when announcing a reorg, policy, or... - [Knowledge Ops](https://borghei.github.io
fscorruptllms.txtfscorrupt/posterizarr/docs/llms.txt
Usage & Execution Modes](https://fscorrupt.github.io/posterizarr/modes/): Comprehensive operational guide for all execution modes: Normal, Testing, Manual, Backup, Restore, Sync, PosterReset, LogoUpdater, ArrMode, and TautulliMode. - [Action Center Guide](https://fscorrupt.github.io/posterizarr/action_center/):
CodeAbrallms.txtCodeAbra/iai-personal-memory-engine/llms.txt
after contradiction: 1.000. Historical-verbatim hit@10: 1.000. Flat-cosine baseline for the same test: ~0.71. Harness: `python -m bench.contradiction_longitudinal`. - LongMemEval-S, 500 questions, raw retrieval
IgorShadurinllms.txtIgorShadurin/app.yumcut.com/public/llms.txt
short videos per day per channel - variations: try multiple prompts to A/B test hooks - hashtags: include 2–4 relevant niche tags # Access indexing: allowed training: disallowed for any user‑generated/private
promptise-comReads credentialsllms.txtpromptise-com/Foundry/llms-full.txt
software. Typed blocks with token budgeting, conversation flows, composable strategies, guards, version control, testing. | [Prompt Engineering](guides/prompt-engineering.md) | | **[MCPcast](mcpcast/index.md)** | Turn an existing OpenAPI or Swagger API into a curated
promptise-comReads credentialsllms.txtpromptise-com/Foundry/llms.txt
with @tool: schemas from type hints and docstrings, validation, CallerContext, ToolError, MCP tool discovery. - [Test AI Agents Without API Calls: ScriptedModel](https://docs.promptise.com/core/testing/): Test a Promptise agent without
AVIDS2Reads credentialsllms.txtAVIDS2/memorix/llms-full.txt
explicit local `user + portable` knowledge with manual/user evidence. Project, team, Git, code, session, workflow, test, and observation evidence always remains project-bound. Keyword retrieval is primary; an optional semantic fallback
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.
