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.
agents-uillms.txtagents-ui/agents-kit/llms-full.txt
packages are pinned to `@livekit/components-react@2.9.24` and `livekit-client@2.22.3`. Use the [LiveKit frontend documentation](https://docs.livekit.io/frontends/) to configure your host application and token source. Generate access tokens
KilbexReads credentialsllms.txtKilbex/Vigla/llms-full.txt
clone the source and run one command: ```sh ./scripts/build.sh ``` The script installs the locked frontend dependencies, builds the application, ad-hoc signs it without an Apple account or personal signing
Kilbexllms.txtKilbex/Vigla/llms.txt
clone the source and run one command: ```sh ./scripts/build.sh ``` The script installs the locked frontend dependencies, builds the application, ad-hoc signs it without an Apple account or personal signing
EliasOulkadillms.txtEliasOulkadi/shokunin/llms.txt
Shokunin AI Ecosystem > 62 skills for AI coding agents. Infrastructure, backend, frontend, mobile, content, quality, productivity, documents, and AI agents. Each skill provides structured workflows, checklists, and domain-specific knowledge
EliasOulkadillms.txtEliasOulkadi/shokunin/.pack/llms.txt
Shokunin AI Ecosystem > 62 skills for AI coding agents. Infrastructure, backend, frontend, mobile, content, quality, productivity, documents, and AI agents. Each skill provides structured workflows, checklists, and domain-specific knowledge
Clawdi-AIllms.txtClawdi-AI/clawdi/llms.txt
Development](https://github.com/Clawdi-AI/clawdi/blob/main/docs/backend-development.md): FastAPI, Alembic, throwaway Postgres tests, and generated API client workflow. - [Frontend Development](https://github.com/Clawdi-AI/clawdi/blob/main/docs/frontend-development.md): TanStack Start dashboard loop, OSS build boundary, and web verification commands
NARUBROWNllms.txtNARUBROWN/spine/llms.txt
# Spine > Agent-oriented guide to understanding Spine and building correct applications with the current
permawebReads credentialsllms.txtpermaweb/HyperBEAM/docs/llms-full.txt
full asynchronous scheduling might complete. This is particularly useful for: * **Web Interfaces:** Building frontends that need to quickly read specific data points from an AO process without waiting
backenlyllms.txtbackenly/backenly/public/llms.txt
outcome to `backend_chat`. 4. Read it back, then `generate_types` for the frontend. ## Tools Exactly **23** tools are advertised; `tools/list` is the authority. Every tool except `backend_chat
rasimmellms.txtrasimme/FlowBoard/llms.txt
docs/concepts/kanban.md) — five-column workflow; lease semantics; subtask depth; blocked-as-flag; archived-vs-trashed - [Frontend Runtime](docs/concepts/frontend-runtime.md) — React task-state convergence; optimistic mutations; `window.appState` bridge rules - [Idea Canvas](docs/concepts/idea-canvas.md) — visual
nirholasReads credentialsllms.txtnirholas/crypto-vision/llms-full.txt
builder at [mcp.ucai.tech](https://mcp.ucai.tech). **Stack:** Python, `mcp`, web3.py --- ## Apps Three frontend applications in `apps/`: ### Dashboard: [apps/dashboard](apps/dashboard) **`crypto-data-aggregator`**: Next.js dashboard for real-time crypto market data visualization
hyperb1issPipes a download into a shellllms.txthyperb1iss/lucidity-mcp/docs/llms-full.txt
# Example Clients Source: https://modelcontextprotocol.io/clients A list of applications that support MCP integrations
sfrangulovPipes a download into a shellllms.txtsfrangulov/claude-code-handbook-ru/llms-full.txt
refactor): не даёт агенту писать код раньше тестов. От Matt Pocock. | **1.1M** | | [anthropics/skills@frontend-design](https://skills.sh/anthropics/skills/frontend-design) | Помогает сделать интерфейс выразительнее. Используй, если результат выглядит шаблонно, например когда
AsiaOstrichllms.txtAsiaOstrich/universal-dev-standards/llms.txt
level 2 - [Forward Derivation Standards | 正向推演標準](https://github.com/AsiaOstrich/universal-dev-standards/blob/main/core/forward-derivation-standards.md): `forward-derivation-standards`, level 2 - [Frontend Design Standards](https://github.com/AsiaOstrich/universal-dev-standards/blob/main/core/frontend-design-standards.md): `frontend-design-standards`, level 3 - [Full Coverage Testing Standards
krzkoPipes a download into a shellllms.txtkrzko/google-cloud-mcp/llms-full.txt
# Example Clients Source: https://modelcontextprotocol.io/clients A list of applications that support MCP integrations
shauryagangradellms.txtshauryagangrade/awesome-ai-prompts/website/llms.txt
devops-deploy](https://awesome-ai-prompts.vercel.app/category/devops-deploy): 15 prompts - [docs-delivery](https://awesome-ai-prompts.vercel.app/category/docs-delivery): 7 prompts - [frontend-ui](https://awesome-ai-prompts.vercel.app/category/frontend-ui): 13 prompts - [git-github](https://awesome-ai-prompts.vercel.app/category/git-github): 14 prompts - [mobile
dcc-mcpReads credentialsllms.txtdcc-mcp/dcc-mcp-core/llms.txt
# dcc-mcp-core > Foundational library for the DCC Model Context Protocol (MCP) ecosystem. Rust
axocoatlPipes a download into a shellllms.txtaxocoatl/axocoatl/llms.txt
workbench browser assets. Those assets are embedded, so using Axocoatl requires no separate frontend install or bundled browser runtime. Rootless Podman remains the local sandbox requirement for repository Sessions. Install
littlebearappsPipes a download into a shellllms.txtlittlebearapps/untether/llms-full.txt
# Untether > Telegram bridge for AI coding agents. Send tasks by voice or text, stream
OpendrayPipes a download into a shellllms.txtOpendray/opendray/llms.txt
binary, cosign-signed releases with SPDX SBOM. ## Not what it is - Not a chat frontend (compare Open WebUI, LibreChat). opendray runs the actual agentic CLI process with tool
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.
