# README

**Control AI coding agents from your favorite messaging platform.**

OpenACP bridges AI coding agents to messaging platforms like Telegram, Discord, and Slack using the [Agent Client Protocol (ACP)](https://agentclientprotocol.com/). Send a message, and your AI agent writes code, runs commands, and streams results back — all from your phone or desktop.

## Why OpenACP?

* **28+ AI agents** — Claude Code, Gemini CLI, Codex, Copilot, Cursor, Cline, goose, and more
* **Any platform** — Telegram, Discord, Slack, or build your own adapter
* **Self-hosted** — Your machine, your API keys, your data. Nothing leaves your infrastructure.
* **Real-time streaming** — Watch your agent think, plan, and execute with live updates
* **Session management** — Persistent sessions, resume after restarts, transfer between devices

## Get Started

Choose the path that fits you:

| I want to...                                    | Start here                                               |
| ----------------------------------------------- | -------------------------------------------------------- |
| **Understand what OpenACP does**                | [What is OpenACP?](/getting-started/what-is-openacp.md)  |
| **Install and start chatting** with an AI agent | [Quick Start](/getting-started/quick-start.md)           |
| **Build plugins & adapters** for OpenACP        | [For Contributors](/getting-started/for-contributors.md) |

Or start with [What is OpenACP?](/getting-started/what-is-openacp.md) to understand the big picture.

## Quick Install

```bash
npm install -g @openacp/cli
openacp
```

***

[![npm](https://img.shields.io/npm/v/@openacp/cli)](https://www.npmjs.com/package/@openacp/cli) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.openacp.ai/readme.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.