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.
glinckerllms.txtglincker/thesvg/public/llms-full.txt
homepage switch that remembers which view you prefer. - [10 SVG Icon Performance Hacks Every Frontend Developer Should Know](https://thesvg.org/blog/svg-icon-performance-hacks-2026) (2026-09-13): Beyond 'use SVG instead
glinckerllms.txtglincker/thesvg/public/llms.txt
Popular](https://thesvg.org/blog/recently-added-and-popular-icons) (2026-10-01) - [10 SVG Icon Performance Hacks Every Frontend Developer Should Know](https://thesvg.org/blog/svg-icon-performance-hacks-2026) (2026-09-13) - [A More Alive Icon Page: Brand Colors
snapotter-hqllms.txtsnapotter-hq/SnapOtter/llms.txt
import/export, IP allowlist, legal hold, SCIM, SIEM, webhooks, GDPR lifecycle, upgrade checks ## Tech Stack Frontend: React 19, Vite 8, Tailwind CSS 4, Zustand Backend: Fastify 5; Sharp (images), FFmpeg (video/audio
1 project uses a version of this
CanineHQllms.txtCanineHQ/canine/public/llms.txt
processes) - `app/controllers/inbound_webhooks/` - Git webhook receivers - `app/controllers/mcp_controller.rb` - MCP server endpoint - `app/controllers/avo/` - Admin panel controllers ### Frontend (app/javascript/controllers/) Stimulus controllers for client-side interactivity: - `terminal_controller.js` - WebSocket-based terminal for pod shell access - `logs_controller.js
No other project uses it yet
Googlellms.txtgoogle-gemini/genai-processors/llms.txt
backend, default to localhost. * create local webpage with JS or TS for the frontend, base64 decode the media data when receiving. * All messages sent and received are JSON-serialized ProcessorParts
No other project uses it yet
NVIDIAllms.txtNVIDIA/aistore/docs/llms.txt
buckets - [S3 Compatibility](https://aistore.nvidia.com/docs/s3compat): Amazon S3 API support — backend and frontend modes - [ETL](https://aistore.nvidia.com/docs/etl): Extract, Transform, Load — run transforms on storage nodes alongside data - [Batch Operations
MicrosoftPipes a download into a shellllms.txtmicrosoft/WhatTheHack/068-AzureOpenAIApps/Student/Resources/data/mcp-info/llms-full.txt
# Example Clients Source: https://modelcontextprotocol.io/clients A list of applications that support MCP integrations
1 project uses a version of this
almeidapauloptllms.txtalmeidapaulopt/tsdproxy/llms.txt
quality with `make audit` - [Source Code](https://github.com/almeidapaulopt/tsdproxy): Go 1.26, templ UI, Vite/Bun frontend, Hugo docs ## Optional - [Sponsor the Project](https://github.com/sponsors/almeidapaulopt): Support ongoing development - [Tailscale](https://tailscale.com
No other project uses it yet
bartblastReads credentialsllms.txtbartblast/hologram/llms-full.txt
transformation, Hologram compiles the necessary parts of your Elixir code to JavaScript, delivering modern frontend functionality without requiring any JavaScript frameworks or direct JavaScript coding. #### Key Features - Pure Elixir development
No other project uses it yet
LING71671Reads credentialsllms.txtLING71671/open-reverselab/docs/llms.txt
bearer credential. This playbook covers token location discovery, URL/Referer/log leakage, XSS and frontend-state capture, replay after logout, cross-device/IP/session replay, refresh-chain p - [red · JWT Library CVEs
ksimbackPipes a download into a shellllms.txtksimback/hermes-ecosystem/llms-full.txt
# Hermes Atlas — Full Context Bundle > Complete content of hermesatlas.com as of 2026-11-15
datadrivenconstructionllms.txtdatadrivenconstruction/OpenConstructionERP/llms.txt
hosted. ## Repo structure - `backend/` - Python 3.12+ / FastAPI API server, 193 modules, Pydantic v2, PostgreSQL - `frontend/` - React 18 / TypeScript SPA, AG Grid, Three.js, PDF.js, Yjs real-time - `services/` - standalone microservices
No other project uses it yet
aegrallms.txtaegra/aegra/docs/llms.txt
same LangGraph SDK and Agent Protocol APIs, so existing graph code, client libraries, and frontends (Agent Chat UI, LangGraph Studio, CopilotKit) work without modification. Self-hosted on your own PostgreSQL
Steady2 mentions in 2 weeks
1 project uses a version of this
reticlehqPipes a download into a shellllms.txtreticlehq/reticle/llms.txt
WCAG audits), a security scanner (vulnerability discovery). ## How it works (architecture) **One engine, many frontends.** The verification engine (session + tools + flows + the verdict artifact) is transport-agnostic; every consumer hits
Steady3 mentions in 2 weeks
No other project uses it yet
asheshgoplaniPipes a download into a shellllms.txtasheshgoplani/agent-deck/llms-full.txt
tmux status bar. Press `Ctrl+b 1-6` to jump directly to them. ``` ⚡ [1] frontend [2] api [3] backend ``` By default the session that started waiting most recently
borgheiReads credentialsllms.txtborghei/Claude-Skills/site/llms.txt
# Claude Skills > The Universal AI Skills Library -- 403 production-ready skills across 21 domains
agentic-communityPipes a download into a shellllms.txtagentic-community/mcp-gateway-registry/docs/llms.txt
scopes` collection in DocumentDB, seeded from JSON scope files in `scripts/` | | `frontend/` | **Web UI** - React/TypeScript admin dashboard | `src/App.tsx` (main app), `src/pages/` (UI pages) | | `servers/` | **Example MCP Servers** - Reference implementations | `currenttime
NVIDIAllms.txtNVIDIA/cudnn-frontend/llms.txt
cuDNN Frontend > NVIDIA cuDNN Frontend (FE): a header-only C++ library and Python package (`nvidia-cudnn-frontend`, import `cudnn`) exposing the cuDNN Graph API, plus open-source CuTeDSL kernels (SDPA/Flash
fscorruptllms.txtfscorrupt/posterizarr/docs/llms.txt
fscorrupt.github.io/posterizarr/backend_python/): FastAPI backend architecture, SSRF protections, SQLite database models, queue manager, and scheduler. - [Frontend Components Reference](https://fscorrupt.github.io/posterizarr/frontend_components/): React 18 component tree, Vite build pipeline, Tailwind CSS design
ningbainbllms.txtningbainb/deepseek-harness-desktop/website/llms.txt
this is not a process-wide memory cap or a general percentage speedup claim. - Frontend reads are asynchronous and coalesced per file while retaining per-request authorization, SPA/HEAD/cache and Windows
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.
