Clients

The following projects implement ACP directly, connect ACP agents to other environments, or support adjacent coding-agent workflows.

​

Editors and IDEs

• Anycode — web-based IDE with Rust backend and React frontend
• Chrome ACP (Chrome extension / PWA)
• Emacs via agent-shell.el
• JetBrains
• neovim
  • through the CodeCompanion plugin
  • through the carlos-algms/agentic.nvim plugin
  • through the yetone/avante.nvim plugin
  • through the hermes.nvim plugin
• Obsidian
  • through the Agent Client plugin
  • through the Agent Console plugin — a tabbed multi-session workspace: run several ACP agents in parallel with restorable, searchable sessions and quick prompts
  • through the Obsidian Harness plugin — Obsidian as a cockpit for ACP agents (Claude Code, Codex, Gemini CLI, Pi); every agent session is a first-class .session vault file with Codex-style Session and Turn navigators
• Pulsar — through the pulsar-acp-agent package
• Qt Creator — through the ACP Client Plugin
• Unity ACP Client(Unity plugin)
• Unity Agent Client (Unity editor)
• Visual Studio — through the Poolside Assistant
• Visual Studio Code
  • ACP Client extension
  • ACP Patchbay extension
  • ACP Pro Extension
    • VS Code–compatible IDEs (Cursor, Windsurf, Trae,..): ACP Pro Extension
  • Multicoder extension
  • Poolside Assistant
• Zed

​

CLI and TUI

• acpx (CLI)
• Hash (shell)
• Hydra
• Nori CLI
• pool
• Toad

​

Desktop and Web

• ACP UI (Windows, macOS, Linux, iOS, Android, Web)
• Agent Studio
• AgentRQ — Human-in-the-loop realtime task management and collaboration (Web)
• AionUi
• aizen
• Braide - Parallel sessions, worktrees, personas and interactive agent responses (supports macOS, Windows, Linux)
• Casper - A web client for kiro-cli that talks to it over the Agent Client Protocol (ACP), giving you a browser-based chat UI with live streaming, session history, and rich per-tool-call rendering.
• Codeg — collaborative multi-agent coding workbench that unifies ACP agents (Claude Code, Codex, Gemini CLI, OpenCode, and more) with session aggregation; desktop app, self-hosted server, or Docker (macOS, Windows, Linux, Web)
• DeepChat
• Devin Desktop
• fabriqa.ai
• gemini-cli-desktop
• Gold Band — open-source, local-first ACP desktop client supporting direct agent conversations, DSL-based workflow orchestration, AI-generated dynamic workflows, and unified context management (Windows, macOS, Linux)
• Harnss
• Jockey — open-source multi-agent orchestrator (Tauri + Rust + SolidJS) that coordinates Claude Code, Gemini CLI, and Codex CLI via ACP
• Lody
• Minion Mind — through the Agent Client plugin
• Mitto
• Ngent
• Poolside Desktop Assistant - An agent agnostic worktree native macOS desktop app.
• qwen-audio-agent — realtime full-duplex voice client for ACP agents, with wake word and barge-in (macOS desktop, TUI, Web)
• RayClaw
• RLM Code
• Shellular (GitHub)
• Sidequery (coming soon)
• Tidewave
• Web Browser with AI SDK (powered by @mcpc/acp-ai-provider)
• Kangaroo — database IDE with Agent Client Protocol support
• ACP Components - A universal frontend component library for building AI Agent interfaces based on the ACP
• ACP Inspector — desktop debugger/inspector for the ACP protocol (macOS, Linux)
• Newio — a multi-channel, multi-player agent native messaging app

​

Notebook and data tools

• agent-client-kernel (Jupyter notebooks)
• DuckDB — through the sidequery/duckdb-acp extension
• marimo notebook

​

Mobile clients

These mobile-first tools bring ACP and related coding-agent workflows to phones and tablets:

• Agmente (GitHub) (iOS)
• Ferngeist (Android)
• Happy (GitHub) (iOS, Android, Web)
• Mobvibe (iOS, Android, Web)
• Shellular (GitHub) (iOS, Android, Web)

​

Messaging

• ACP Discord (Discord)
• duckdb-claude-slack (Slack)
• Juan (Slack)
• OpenACP (Telegram, Discord, Slack) — self-hosted bridge for ACP agents; streams tool calls and responses in real time
• Telegram ACP Bot (Telegram) — through the telegram-acp-bot connector
• Telegram-ACP (Telegram) — Supports multi-thread chat and message streaming
• ACP Router (Telegram) - an ACP client surface for driving ACP agents from Telegram, with rich diffs, approvals and many more.
• WeChat ACP (WeChat)
• qq-ai-bot (QQ / OneBot 11) — self-hosted bridge for OneBot 11 / NapCat / LLOneBot that connects QQ messaging to ACP-compatible agents with persistent sessions and progress streaming
• Sniptail (Discord, Slack) - self-hosted chat bridge for running coding agents across your team’s repositories
• Lark ACP (Lark/飞书)
• Zooid (Matrix) - coding agent runtime paired with a Matrix client/ACP bridge for interacting with agents
• Pomerium AgentOps (Slack)

​

Frameworks

These frameworks add ACP support through dedicated integrations or adapters:

• AgentPool — with built-in ACP integration for IDEs and external ACP agents
• fast-agent — through fast-agent-acp
• ACP Kit - adapter toolkit for exposing existing Pydantic AI / LangChain agent runtimes through ACP.
• Koog — through the agents-features-acp integration
• LangChain / LangGraph — through Deep Agents ACP
• LlamaIndex — through the workflows-acp adapter for Agent Workflows
• LLMling-Agent — with built-in ACP support for running agents through ACP clients
• Mastra — through the @mastra/acp package for wrapping external ACP agents as tools or subagents

​

Connectors

These connectors bridge ACP into other environments and transport layers:

• ACP to AG-UI — bridges any ACP agent to web frontends via AG-UI events over SSE; works with CopilotKit, AG-UI HttpAgent, or custom UIs (Web)
• AgentRQ — bridges stdio-based ACP agents to the AgentRQ - Human-in-the-loop task collaboration service using MCP server.
• Aptove Bridge — bridges stdio-based ACP agents to the Aptove mobile client over WebSocket
• ACP Remote - remote WebSocket transport for ACP agents and clients.
• OpenClaw — through the openclaw acp bridge to an OpenClaw Gateway
• stdio Bus – deterministic stdio-based kernel providing transport-level routing for ACP/MCP-style agent protocols.
• acpdbg — bridges LLDB crashes (C/C++/Rust/Swift) to any ACP coding agent for root-cause analysis and live debugging