Provides integration of any AI agent (Gemini CLI, Claude Code, Codex CLI, etc.) with the Unity editor using Agent Client Protocol
# Unity Agent Client [](./LICENSE)  English | [日本語](README_JA.md) Provides integration of any AI agent (Gemini CLI, Claude Code, Codex CLI, etc.) with the Unity editor using Agent Client Protocol(ACP).  ## Overview Unity Agent Client is an editor extension that uses the Agent Client Protocol (ACP) proposed by Zed to enable any AI agent to run on the Unity editor. ### Features - Integrate any AI agent into the Unity editor - Supports all AI agents compatible with ACP (Gemini CLI, Claude Code, Codex CLI, etc.) - Utilize assets and editor information as context - Provides a built-in MCP server ### What's Agent Client Protocol? <img src="https://camo.githubusercontent.com/7de78d0f4d0f9755d0ed1aef979e0758dc64790f9c14831d0445d92dc6f36666/68747470733a2f2f7a65642e6465762f696d672f6163702f62616e6e65722d6461726b2e77656270"> [Agent Client Protocol](https://agentclientprotocol.com) is a new protocol proposed by Zed to connect AI agents and code editors. It is a protocol based on JSON-RPC and is designed with integration with MCP (Model Context Protocol) in mind. Zed enables the integration of external AI agents into editors using ACP. Unity Agent Client adopts a similar approach, implementing an ACP Client as an editor extension, allowing any AI agent to run on the Unity editor. Currently, Gemini CLI provides experimental support (`--experimental-acp`), and Zed's adapters enable ACP compatibility for Claude Code, Codex CLI, and others. A list of AI agents supporting ACP can be found at the following page: https://agentclientprotocol.com/overview/agents ### Why not Unity AI? From Unity 6.2 onwards, the official [Unity AI](https://unity.com/products/ai) can be used. So why use Unity Agent Client? Unity AI uses models provided by Unity, which means users cannot choose the optimal model
Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.