Open-source alternative to Claude Cowork - Universal AI agent platform for completing tasks with AI. Model-agnostic (Claude, Gemini, OpenAI, Ollama), plan-mode by default, sandboxed file ops, browser automation.
# OpenWork <div align="center"> **AI-powered task automation for everyone** Complete tasks like developers use Claude Code, Codex, or Gemini CLI - but with a friendly interface designed for non-technical users. [](https://opensource.org/licenses/MIT) [](https://www.typescriptlang.org/) [](https://www.electronjs.org/) [](CONTRIBUTING.md) [Quick Start](#quick-start) | [Features](#features) | [Documentation](#documentation) | [Contributing](#contributing) </div> --- ## Why OpenWork? **Problem:** Powerful AI coding tools like Claude Code, Codex, and Gemini CLI are built for developers. Non-technical users miss out on AI-powered task automation. **Solution:** OpenWork brings the same power to everyone through a simple desktop app. | Feature | Gemini Cowork | OpenWork | |---------|---------------|----------| | License | Proprietary | **MIT (Open Source)** | | Price | $200/month | **Free** | | Models | Gemini only | **Any provider** (Gemini, GPT, Gemini, Local) | | Self-hosting | No | **Yes** | | Customization | Limited | **Full source access** | ## Quick Start Get running in under 2 minutes: ### Prerequisites - [Node.js 20+](https://nodejs.org/) - [pnpm 9+](https://pnpm.io/installation) (`npm install -g pnpm`) - API key from any provider (or use [Ollama](https://ollama.ai/) for free local models) ### Install and Run ```bash # Clone the repo git clone https://github.com/openwork-ai/openwork.git cd openwork # Install dependencies pnpm install # Set up your API keys cp .env.example .env # Edit .env and add at least one API key # Launch the app pnpm dev:desktop ``` ### First Task 1. **Select a folder** - Choose where OpenWork can read/write files 2. **Pick a provider** - Gemini, Gemini, O
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.