How real projects summarise themselves for language models.
PIsbergllms.txtPIsberg/vibetags/llms.txt
warnings - [docs/PLATFORMS.md](docs/PLATFORMS.md): generated file ↔ platform ↔ format table, granular-rules notes - [docs/TESTS.md](docs/TESTS.md): which test class covers what - [docs/DEPENDENCIES.md](docs/DEPENDENCIES.md): every third-party artifact and why it is here; what
sgroy10llms.txtsgroy10/speclock/llms-full.txt
Your AI remembers your rules — SpecLock makes it obey them. 51 MCP tools, 1043 tests, 0 false positives. SpecLock is the only tool that stops AI coding assistants from breaking
sgroy10llms.txtsgroy10/speclock/llms.txt
/sgroy10/speclock) - **Official MCP Registry:** io.github.sgroy10/speclock - **Website:** [sgroy10.github.io/speclock](https://sgroy10.github.io/speclock/) - **Smithery:** [sgroy10/speclock](https://smithery.ai/servers/sgroy10/speclock) - **Tests:** 1043 tests across 24 suites, 0 false positives - **MCP Tools:** 51 ## Key Features - Semantic conflict
AreevAIllms.txtAreevAI/areev/llms.txt
Intel NUC does it in 30 µs. - **Quality is measured, not asserted.** **2,435 test functions** over 82,944 source lines (test code is 37.7% of the tree); **81.0% line
12errhllms.txt12errh/zen-proxy/llms-full.txt
machine's real IP) - **A retro-zine management dashboard** — stats, one-click model tests, live config, and logs at `http://127.0.0.1:8787/` - **One-file install** on Linux, macOS, and Windows
12errhllms.txt12errh/zen-proxy/llms.txt
jsonc { "provider": { "zen": { "baseURL": "http://127.0.0.1:8787/v1", "apiKey": "public", "models": { "space-bunny-free": {} } } } } ``` Quick test: ```bash curl -s http://127.0.0.1:8787/v1/chat/completions \ -H "Content-Type: application/json" \ -d '{"model":"space-bunny-free
dalrootllms.txtdalroot/agentic-seo/docs/llms-full.txt
HTML directly. 2. **Deterministic Evidence vs. Guesswork**: All evaluations run local, verified Python scripts (testing robots.txt, Core Web Vitals, hreflang, link health) to avoid hallucinated recommendations. 3. **Zero Subscription Lock
khaskyllms.txtkhasky/awesome-agents-md/llms.txt
/khasky/awesome-agents-md/blob/main/rules/code-review.md): reviewing a diff/PR, severity triage, comment format, receiving review. - [rules/testing.md](https://github.com/khasky/awesome-agents-md/blob/main/rules/testing.md): test placement ladder, fixtures, flakiness, fuzz and property tests. - [rules/evidence-gates.md](https://github.com/khasky/awesome-agents-md/blob/main/rules/evidence-gates.md): turning a verification
sandraschillms.txtsandraschi/ocr-mcp/llms.txt
real vs mock ## Install and run - **Justfile**: `just` to list recipes; `just run`, `just test`, `just webapp`, `just install` ([just](https://github.com/casey/just)) - **Recommended**: `uv run ocr-mcp` (from repo
andreibesleagallms.txtandreibesleaga/GABBE/llms.txt
NIST AI RMF / MITRE ATLAS / ISO 42001 / EU AI Act), **advanced testing** (property-based, metamorphic, chaos/fault-injection, mutation; `gabbe verify --chaos`), and a **verified one-command, multi-OS install** with environment/agent
arikusillms.txtarikusi/nakkas/llms-full.txt
modelcontextprotocol/sdk * zod (schema validation + type generation) * Pure XML string construction.no SVG library dependencies * Vitest test suite (296 tests) ## Pattern Elements ### radial-group Places N instances of one child element around
backenlyllms.txtbackenly/backenly/public/llms.txt
oauth_provider`, `list_users`, `reset_password`, `unblock_user`, `enable_teams`, `email_settings`, `set_smtp`, `test_smtp`, `set_email_template`, `reset_email_template`; `remove_oauth_provider`, `block_user`, `remove_smtp` wait
CorpusIQllms.txtCorpusIQ/corpusiq-docs/llms-full.txt
category. Use this guide when you have a concrete request, bug report, recipe, or tested example ready to track. --- ## Enhancement Requests Use the issue tracker. Do not open freeform issues
heymegabytellms.txtheymegabyte/claude-skills/llms-full.txt
category map · task routing · file hints) - [Skill Packs](_packs/README.md) — grouped bundles (core / frontend / backend / testing / design / …); one pack loads its whole graph - [Kernel](_kernel/index.md) — canonical shared definitions (WCAG · OWASP
heymegabytellms.txtheymegabyte/claude-skills/llms.txt
category map · task routing · file hints) - [Skill Packs](_packs/README.md) — grouped bundles (core / frontend / backend / testing / design / …); one pack loads its whole graph - [Kernel](_kernel/index.md) — canonical shared definitions (WCAG · OWASP
imMamdouhaboammarllms.txtimMamdouhaboammar/chatgpt-codex-plugin-autopilot/llms.txt
analyzer - [skills/chatgpt-codex-plugin-autopilot/scripts/validate_plugin.py](https://github.com/imMamdouhaboammar/chatgpt-codex-plugin-autopilot/blob/main/skills/chatgpt-codex-plugin-autopilot/scripts/validate_plugin.py): Plugin package validator - [skills/chatgpt-codex-plugin-autopilot/scripts/package_plugin.py](https://github.com/imMamdouhaboammar/chatgpt-codex-plugin-autopilot/blob/main/skills/chatgpt-codex-plugin-autopilot/scripts/package_plugin.py): Plugin packager ## Tests - [tests/](https://github.com/imMamdouhaboammar/chatgpt-codex-plugin-autopilot/tree/main/tests): 92 regression tests covering plugin contract, validator, distribution pack, skill surface
ShieldNet-360llms.txtShieldNet-360/secure-vibe/docs/llms-full.txt
SecureVibe's own tuned corpus ("on the shapes we tested")**. The honest signal here is gitleaks' *recall gap*, not a universal claim of superiority. - **The three structured scanners (deps / Dockerfile
ShieldNet-360llms.txtShieldNet-360/secure-vibe/docs/llms.txt
shieldnet-360.github.io/secure-vibe/changelog/) ## Guides - [Choose your path](https://shieldnet-360.github.io/secure-vibe/guides/): evaluator / developer / devops / security / contributor - [Test with a model](https://shieldnet-360.github.io/secure-vibe/guides/testing-with-models/): run the prevention-lift eval keyless (Ollama
AnayDhawanllms.txtAnayDhawan/openvidstudio/llms.txt
newest first. ## Contributing - [CONTRIBUTING](https://github.com/AnayDhawan/openvidstudio/blob/main/CONTRIBUTING.md): setup, the verification commands (`pnpm --filter build`/`test`), and what a good pull request looks like. - [Code of Conduct](https://github.com/AnayDhawan/openvidstudio/blob/main/CODE_OF_CONDUCT.md) - Good
spectrayanllms.txtspectrayan/spector/docs/llms.txt
heap: Project Panama FFM API - Concurrency: Virtual Threads (Project Loom) - Modules: 25 Maven modules - Tests: 685+ tests - Dependencies: Zero (JDK only
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.
