This project provides an open-source, multi-provider AI chatbot client designed for an intuitive user experience, integrating external tools via the Model Context Protocol (MCP). It targets users seeking a flexible and powerful AI chat interface, enabling features like real-time voice interaction, browser automation, and quick tool mentions.

How It Works

The client is built with Next.js and the Vercel AI SDK, leveraging the Model Context Protocol (MCP) for seamless tool integration. It allows LLMs to autonomously select and utilize tools from an MCP server, facilitating multi-step tasks. Features like quick tool mentions (@toolname) and configurable "Tool Choice Modes" (Auto, Manual, None) offer granular control over AI interaction.

Quick Start & Requirements

• Installation: Recommended package manager is pnpm. Install with npm install -g pnpm.
• Dependencies: Requires API keys for LLM providers (OpenAI, Google Generative AI, Anthropic, etc.) and optionally PostgreSQL.
• Setup: Docker Compose is recommended for a quick start. Local setup involves installing dependencies, configuring .env with API keys, and running migrations.
• Links: Guides, Discord

Highlighted Details

• Real-time voice assistant with MCP tool integration.
• Browser automation via Playwright MCP.
• Quick tool mentions (@) and customizable tool presets.
• Configurable "Tool Choice Mode" for AI interaction control.

Maintenance & Community

• Active community engagement via Discord.
• Contributions are welcomed for bug reports, features, and translations.
• Roadmap includes LLM workflows, file attachments, collaborative editing, RAG, and web compute.

Licensing & Compatibility

• The license is not explicitly stated in the README.

Limitations & Caveats

• The project is actively under development with a roadmap indicating planned features.
• Specific licensing details for commercial use or closed-source linking are not provided.