Nanobrowser is a Chrome extension for AI-powered web automation that runs locally in your browser.
The tool addresses the need for affordable, privacy-preserving web automation by deploying a multi-agent system directly in your browser. Rather than sending requests to a cloud service, Nanobrowser executes AI workflows locally using your own LLM API keys. The system uses specialized agents that collaborate to accomplish complex tasks—a Planner agent that reasons about goals and self-corrects when encountering obstacles, and a Navigator agent that executes instructions on web pages. You interact through an intuitive side panel chat interface where you can describe tasks, receive real-time status updates, ask follow-up questions, and review conversation history.
Nanobrowser suits developers and users who want web automation without subscription costs or privacy concerns. It works best for those comfortable managing their own LLM API keys and who prefer flexibility in choosing which models power different agents. The tool supports OpenAI, Anthropic, Gemini, Ollama, Groq, Cerebras, Llama, and custom OpenAI-compatible providers. Unlike OpenAI Operator, which operates as a hosted service with fixed pricing, Nanobrowser is fully open source and free to install, with costs determined only by your own API usage. The extension officially supports Chrome and Edge with full feature parity.
Development activity shows consistent engagement with the project. The maintainers actively solicit community input through Discord and social channels, indicating responsiveness to user needs. The codebase is written in TypeScript and remains open to contributions, with the team maintaining a sponsorship option for those wanting to support ongoing development. Regular updates to supported LLM providers demonstrate the project's evolution in response to the expanding ecosystem of AI models.
