web-ui

Why we included this project

Most browser automation tools keep you at arm's length from what the agent is actually doing. This one puts a Gradio interface on top of the browser-use library, so you type a task, pick a model, and watch the agent work through pages in a real browser window. It supports a wide range of LLM providers, from OpenAI and Anthropic to DeepSeek and Ollama, so you are not tied to one vendor. You can also point it at your own installed browser profile, which saves you from re-logging into sites or fighting authentication walls, and persistent sessions keep the window open between tasks so the full history stays visible. For teams that want to demo or operate browser automation without writing glue code, it is a practical starting point, and the Docker setup makes local deployment painless.