explaingit

browseros-ai/browseros

10,912TypeScriptAudience · vibe coderComplexity · 3/5LicenseSetup · moderate

TLDR

BrowserOS is an open-source Chromium-based browser with a built-in AI agent that navigates websites, automates tasks, and controls your computer using plain-language instructions, connect your own API key or run a local model.

Mindmap

mindmap
  root((BrowserOS))
    What it does
      AI browser agent
      Workflow builder
      Task scheduling
    Tech Stack
      Chromium TypeScript
      MCP server
      Local AI models
    Use Cases
      Web automation
      Form filling
      AI comparison
    Features
      Memory across sessions
      Ad blocking
      CLI control
Click or tap to explore — scroll the page freely

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

Things people build with this

USE CASE 1

Automate repetitive web tasks like form filling and data extraction using plain English commands

USE CASE 2

Set up scheduled browser workflows that run automatically on a timer

USE CASE 3

Compare AI responses from Claude, ChatGPT, and Gemini side by side on any webpage

USE CASE 4

Connect AI coding tools like Claude Code to a browser via MCP server for remote web automation

Tech stack

TypeScriptChromiumNode.js

Getting it running

Difficulty · moderate Time to first run · 30min

Requires your own API key from Claude, OpenAI, or Gemini, or a locally running Ollama or LM Studio model.

Free to use and modify, but any modified version you distribute must also be released as open source under the AGPL license.

In plain English

BrowserOS is an open-source web browser built on Chromium (the same foundation as Google Chrome) that has AI agent capabilities built directly into it. It is available for macOS, Windows, and Linux. You connect your own API key from providers like Claude, OpenAI, or Gemini, or you can run a local AI model on your own computer using tools like Ollama or LM Studio. Your data does not leave your machine when using local models. The core feature is an AI agent that can control the browser for you. It understands plain-language instructions and can navigate pages, click buttons, fill forms, and pull data from websites. It has over 53 tools for this kind of browser automation. There is also a visual builder for creating repeatable workflows, so you can chain together a series of actions and run them again later without repeating the instructions each time. BrowserOS includes a feature called Cowork, which lets the AI agent work with both websites and files on your computer at the same time. For example, it can research something on the web and save a summary to a folder on your machine. You can also schedule tasks to run automatically on a timer. A memory feature lets the assistant remember context from previous conversations rather than starting fresh every time. The browser exposes an MCP server, which means other AI coding tools (like Claude Code or Gemini CLI) can control the browser remotely through a standard interface. It also has an LLM Hub that lets you compare responses from Claude, ChatGPT, and Gemini side by side on any page. Ad blocking is included, and the project states it provides stronger protection than Chrome by default. You can import bookmarks, passwords, and extensions from an existing Chrome installation. A command-line tool called browseros-cli is available for controlling the browser from a terminal or from AI coding agents. The project is licensed under AGPL v3.

Copy-paste prompts

Prompt 1
Using BrowserOS with its 53+ browser automation tools, write a workflow that logs into a website, searches for a product, and saves the results to a local file
Prompt 2
Help me set up the BrowserOS MCP server so Claude Code can control my browser to automate research tasks
Prompt 3
Create a scheduled BrowserOS task that runs every morning, checks a news site, and saves a summary to a local markdown file using the Cowork feature
Prompt 4
Using BrowserOS with a local Ollama model, build a workflow that fills out a web form based on data from a spreadsheet on my computer
Prompt 5
Show me how to import my Chrome bookmarks and extensions into BrowserOS and configure an OpenAI API key for the AI agent
Open on GitHub → Explain another repo

← browseros-ai on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.