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.
sirkirbyllms.txtsirkirby/unifi-network-mcp/docs/llms.txt
only within the tool family that returned them unless an explicit resolver documents a verified bridge. ## Getting Started - [Quick start](https://github.com/sirkirby/unifi-mcp/blob/main/QUICKSTART.md): Install and configure a local MCP server
NVIDIAllms.txtNVIDIA/cudnn-frontend/llms.txt
SDPA/Flash Attention, MoE grouped-GEMM fusions, fused normalizations) for Hopper and Blackwell GPUs. Published documentation: https://docs.nvidia.com/deeplearning/cudnn/latest/developer/overview.html ## Start here - [README](https://github.com/NVIDIA/cudnn-frontend/blob/main/README.md): overview, installation, feature highlights - [AGENTS.md
umputunllms.txtumputun/revdiff/site/llms.txt
revdiff > TUI for reviewing diffs, files, and documents with inline annotations revdiff is a terminal-based UI for code review and document annotation. It displays diffs from Git, Mercurial
Electricitysheepllms.txtElectricitysheep/dsh-handbook/llms-full.txt
guide, plugin development, plugin 开发, sandbox security, cache hit rate, cost optimization, agent benchmark. ## Documentation - [Chinese README (canonical)](README.md) - [English README](README.en.md) - [Online docs site (searchable)](https://electricitysheep.github.io/dsh-handbook/) - [Cheatsheet
Electricitysheepllms.txtElectricitysheep/dsh-handbook/llms.txt
guide, plugin development, plugin 开发, sandbox security, cache hit rate, cost optimization, agent benchmark. ## Documentation - [Chinese README (canonical)](README.md) - [English README](README.en.md) - [Online docs site (searchable)](https://electricitysheep.github.io/dsh-handbook/) - [Cheatsheet
Vrun-designllms.txtVrun-design/openflowkit/public/llms.txt
only the canvas changes, canonically numbered. "The box I selected" is `selection` in `get_document`. ## Draw this repo's architecture `discover_architecture` with `{ path }` proposes a C4 workspace (`dsl`) from
duriantacoReads credentialsllms.txtduriantaco/skylos/llms-full.txt
skylos agent scan . --changed` - LLM app defense: `skylos defend .` ## Official links - Website: https://skylos.dev - Documentation: https://docs.skylos.dev - GitHub: https://github.com/duriantaco/skylos - PyPI: https://pypi.org/project/skylos/ - GitHub Action: https://github.com/duriantaco/skylos/blob/main/action.yml
duriantacoReads credentialsllms.txtduriantaco/skylos/llms.txt
metadata: https://github.com/duriantaco/skylos/blob/main/pyproject.toml - Changelog: https://github.com/duriantaco/skylos/blob/main/CHANGELOG.md ## Best official pages - Website: https://skylos.dev - Documentation: https://docs.skylos.dev - GitHub: https://github.com/duriantaco/skylos - PyPI: https://pypi.org/project/skylos/ - GitHub Action: https://github.com/duriantaco/skylos/blob/main/action.yml
JuliusBrusseellms.txtJuliusBrussee/caveman-code/llms.txt
backed memory. This file is the LLM-friendly entry point to Caveman Code's documentation. Each linked page is plain markdown. ## Install ``` npm install -g @juliusbrussee/caveman-code ``` Requires Node.js 20+. Binaries
GarethManningllms.txtGarethManning/claude-education-skills/llms.txt
planned three-layer education AI system (skill library → context engine → orchestrator). ## Key Documentation - [README.md](https://github.com/GarethManning/education-agent-skills/blob/main/README.md): Full overview, architecture, usage, and domain table - [ARCHITECTURE.md](https://github.com/GarethManning/education-agent-skills/blob/main/docs/ARCHITECTURE.md): Three-layer
AVIDS2Reads credentialsllms.txtAVIDS2/memorix/llms-full.txt
Memorix - Full AI-Facing Documentation Summary > Local-first shared memory layer for AI coding agents. Memorix is a TypeScript/Node.js project that gives AI coding agents persistent, project-aware memory
fluffyponyPipes a download into a shellllms.txtfluffypony/dothething/llms.txt
working until the job is finished. It handles research, analysis, report writing, data extraction, document processing, and system administration. Licensed under BSD 3-Clause. dothething routes all model calls through
fscorruptllms.txtfscorrupt/posterizarr/docs/llms.txt
multi-process lifecycle, run modes, database schemas, rendering engine, REST endpoints, and conventions. ## Core Documentation & Deployment - [Requirements](https://fscorrupt.github.io/posterizarr/requirements/): Host prerequisites including ImageMagick 7, PowerShell 7+, Python 3.13, memory
unbrowse-aiReads credentialsllms.txtunbrowse-ai/unbrowse/llms.txt
breaks (the CLI prints "This looks like a bug in Unbrowse", a 5xx, a documented flag or exit code that misbehaves), follow the `unbrowse-contribute` skill: `unbrowse bug` writes
open-webuillms.txtopen-webui/docs/static/llms.txt
Open WebUI Docs Open WebUI documentation is available as regular HTML and raw Markdown. Start at https://docs.openwebui.com/sitemap.xml to discover pages. For any docs page, append `.md` for Markdown
CodeAbrallms.txtCodeAbra/iai-personal-memory-engine/llms.txt
install --with-tools` from a source checkout. See [docs/DEPLOYMENT.md](docs/DEPLOYMENT.md). ## Docs - [README.md](README.md): full documentation, English. - [README_zh-CN.md](README_zh-CN.md): Chinese. - [CHANGELOG.md](CHANGELOG.md): release history. - [docs/DEPLOYMENT.md](docs/DEPLOYMENT.md): deployment. - [docs/EMBEDDERS.md](docs/EMBEDDERS.md): swappable embedders
pnpllms.txtpnp/powershell/pages/llms.txt
Teams, Microsoft Planner, Microsoft Power Platform, Microsoft Entra, Microsoft Purview, and Microsoft Search. This documentation site is the canonical public reference for installing, authenticating, and using PnP PowerShell cmdlets. ## Start
kinopio-clubllms.txtkinopio-club/kinopio-client/public/llms.txt
builds spatial memory. ## What it is not Not a structured diagramming tool. Not a document editor or database. No AI generation. ## Common Use Cases - you need to connect and organize
cryxnetReads credentialsllms.txtcryxnet/DeepMCPAgent/llms-full.txt
every agent - [Public API Index](reference/public-api.md): Every name Promptise exports, and the page that documents it - [Environment Variables](reference/environment-variables.md): Every variable Promptise reads or sets ================================================================================ Page: Quick Start: Build Your
cryxnetReads credentialsllms.txtcryxnet/DeepMCPAgent/llms.txt
Docs: Build AI Agents and MCP Servers in Python](https://docs.promptise.com/): Promptise Foundry documentation: build AI agents, MCP servers and autonomous agent runtimes in Python, with quickstarts, guides
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.
