Multi-agent GUI for AI coding assistants — Claude Code, Gemini CLI, OpenCode & more. npx agentgui
# AgentGUI [](https://www.npmjs.com/package/agentgui) [](https://www.npmjs.com/package/agentgui) [](LICENSE) [](https://anentrypoint.github.io/agentgui/) Multi-agent GUI client for AI coding agents with real-time streaming, WebSocket sync, and SQLite persistence. ### Supported Agents | Agent | Protocol | Auto-installable | |-------|----------|-----------------| | Claude Code | CLI | - | | OpenCode | ACP | `opencode-ai` | | Gemini CLI | ACP | `@google/gemini-cli` | | Kilo Code | ACP | `@kilocode/cli` | | Goose | ACP | - | | OpenHands | ACP | - | | Augment Code | ACP | - | | Cline | ACP | - | | Kimi CLI | ACP | - | | Qwen Code | ACP | - | | Codex CLI | ACP | - | | Mistral Vibe | ACP | - | | Kiro CLI | ACP | - | | fast-agent | ACP | - |  ## Why AgentGUI? Modern AI coding requires juggling multiple agents, each in their own terminal. AgentGUI solves this by providing a unified interface where you can: - **Compare agents side-by-side** - Test the same prompt across Claude Code, Gemini CLI, OpenCode, and others - **Preserve context** - Every conversation, file change, and terminal output is automatically saved - **Resume interrupted work** - Pick up exactly where you left off, even after system restarts - **Work visually** - See streaming responses, file changes, and tool calls in real-time instead of raw JSON ## Features - 🤖 **Multi-Agent Support** - 14 agents: Claude Code, Gemini CLI, OpenCode, Kilo, Goose, OpenHands, Augment, Cline, Kimi, Qwen, Codex, Mistral Vibe, Kiro, fast-agent - ⚡ **Real-Time Streaming** - Watch agents work with live streaming output and tool calls via WebSocket - 💾 **Session Persistence** - Full conversation history stored in SQLit
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.