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.
nirholasllms.txtnirholas/vscode-google-cloud/llms-full.txt
gcloud compute zones list` ## Examples ### Run 5 instances for different projects ```bash ./gcp-vscode.sh create frontend-app ./gcp-vscode.sh create backend-api ./gcp-vscode.sh create ml-training e2-standard-16 # beefier VM ./gcp-vscode.sh
BubblegunnPipes a download into a shellllms.txtBubblegunn/ai-slop-linter/llms-full.txt
Founding engineer, [Cendra](https://cendra.ai)** (Aug 2025 to Jul 2026): primary author of the frontend. ``` There is no dependable signal in the bold span alone that separates this structural
nodaroaillms.txtnodaroai/app.nodaro.ai/docs/llms.txt
step DAGs that run autonomously on a server. Nodaro is a Fastify backend + Vite/React frontend, source-available under the [Nodaro Sustainable Use License](https://github.com/nodaroai/app.nodaro.ai/blob/main/LICENSE). The backend is REST
daftAI2026llms.txtdaftAI2026/awesome-jev/public/llms-full.txt
# Awesome JEV > Awesome JEV (awesome-jev): a free GitHub directory for TypeSafe Jev / System
bablsoftllms.txtbablsoft/accessflow/website/llms.txt
payloads, WebSocket events - [Backend](https://raw.githubusercontent.com/bablsoft/accessflow/main/docs/05-backend.md): Modular backend, proxy engine, workflow state machine - [Frontend](https://raw.githubusercontent.com/bablsoft/accessflow/main/docs/06-frontend.md): React/Vite layout, SQL editor, TanStack & Zustand - [Security](https://raw.githubusercontent.com/bablsoft/accessflow/main/docs/07-security.md): JWT, SAML
bradleybond512llms.txtbradleybond512/crystal-ball/public/llms-full.txt
temporal windows against learned baselines with per-term spike multipliers and cooldowns ## Tech Stack - **Frontend**: TypeScript, Vite, MapLibre GL JS, deck.gl (WebGL), D3.js, Supercluster (marker clustering), Transformers.js (browser-side
bradleybond512llms.txtbradleybond512/crystal-ball/public/llms.txt
builds are experimental, and CI is not proof of packaged runtime parity. ## Tech Stack - **Frontend**: TypeScript, Vite, MapLibre GL JS, deck.gl, D3.js, Transformers.js (browser-side ML) - **Internationalization**: i18next with lazy
fracturedringllms.txtfracturedring/renpy-mcp/llms.txt
gui/frontend/src/api/client.ts): fetch wrapper; use `api ("/api/...", {json, method})` for every call - [gui/frontend/src/api/types.ts](gui/frontend/src/api/types.ts): shared frontend types that mirror MCP tool responses - [tests/](tests/): pytest suite, 378 tests, ~10s full
JoahanMoralesReads credentialsllms.txtJoahanMorales/upiixia-agentic-kit/llms.txt
call (`uak next` ~2 s on GitHub) and `uak wait` instead of polling; a frontend gate (`product-ui` skill, `uak design-lint` after every UI edit, a design lock picked
nirholasllms.txtnirholas/pumpfun-creator-rewards/llms-full.txt
frontend-api-v3.pump.fun/users/{username|wallet}`: username → wallet These are the same endpoints the live pump.fun frontend calls. Not affiliated with Pump.fun. ## Local dev ```bash npm install npm run dev # vite
vivekchandllms.txtvivekchand/flywheel.md/llms-full.txt
tool: https://flywheel.md/examples/cli-tool.md - Library: https://flywheel.md/examples/library.md - Web service: https://flywheel.md/examples/web-service.md - Frontend app: https://flywheel.md/examples/frontend-app.md - ML project: https://flywheel.md/examples/ml-project.md ## How agents load it No coding tool
vivekchandllms.txtvivekchand/flywheel.md/llms.txt
service](https://flywheel.md/examples/web-service.md): A FLYWHEEL.md for a deployed backend service. - [Frontend app](https://flywheel.md/examples/frontend-app.md): A FLYWHEEL.md for a user-facing web app. - [ML project](https://flywheel.md/examples/ml-project.md):
danieltamasPipes a download into a shellllms.txtdanieltamas/run.dev/llms.txt
crash diagnosis via Claude. ## Who it's for Developers running multiple services locally — microservices, frontends, APIs. Anyone tired of opening 6 terminal tabs every morning and fighting "address already
sandraschillms.txtsandraschi/mixx-dj-mcp/llms.txt
pack . dist/mixx-dj-mcp.mcpb # Build MCPB bundle ``` ## Ports | Port | Service | |------|---------| | 11116 | Backend (FastMCP HTTP + REST) | | 11117 | Frontend (Vite dev server) | | 11118 | Mixxx OSC output (feedback from Mixxx) | | 11119 | Mixxx OSC input (commands
confused-aiReads credentialsllms.txtconfused-ai/personaforge/docs/llms-full.txt
# personaforge — Full Documentation > This file is the complete, machine-readable documentation for personaforge (1.1.0
lacymorrowllms.txtlacymorrow/juno/LLMs.txt
single source of truth for architecture rules, the backend-owns-logic / frontend-is-display boundary, build and test commands, and the rule that Rust is compiled and checked
nirholasReads credentialsllms.txtnirholas/three-ui/llms-full.txt
jobs handle scheduled blockchain operations (ERC-8004 crawl, DCA execution, subscription execution). --- ## Tech Stack **Frontend** | Technology | Version | Purpose | |---|---|---| | three.js | r176 | WebGL 2.0 rendering | | Vite | 7.3.2 | Build tooling + HMR | | Vitest
txn2Reads credentialsllms.txttxn2/mcp-data-platform/docs/llms-full.txt
# mcp-data-platform > MCP server for AI-assisted data exploration. Its own data catalog
txn2Deletes or force-pushesllms.txttxn2/mcp-data-platform/docs/llms.txt
rendered family (HTML, JSX, markdown, SVG) is verified against a live stack by `make frontend-e2e-public-viewer`, which make verify-release runs against its acceptance stack and make verify
yerdaulet-damirllms.txtyerdaulet-damir/vibe-coding-rules/llms.txt
applications, eight Claude Code skills (debug-backend, new-feature, split-monolith, add-provider, debug-frontend, new-feature-nextjs, debug-go, new-feature-go), a `CLAUDE.md` file with authoritative instructions
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.
