Browser Operator [Chromium DevTools with Agentic Framework]

Chromium browser with an user interface to run multi-agent workflows directly on the browser using a stateful, orchestration framework.

Quick Start

Download the Agentic Browser for MacOS

Or

Set up the chromium dev tools with Agent framework on your system

Note: Read this document to know more about the build

Key Capabilities

• Built in Agent Framework for running tasks / workflows.
• Ability to perform actions such as: Navigate URLs, Perform Actions (Clicks, Fill Form, Scroll).
• Access to rendered web page with ability to summarize content.
• Integrates with LLM Models (OpenAI GPT-4.1 and O4-Mini Models).
• Customize workflows or agent behavior with config changes.

Demos

Watch Browser Operator in action with our demo videos:

Deep Research

Browser Operator seamlessly integrates public web data with your private documents and knowledge bases, creating comprehensive research without switching between tools.

Deep.Research.PSPs.mp4

Product Discovery & Comparison

Streamline your shopping research by automatically gathering specifications, user ratings, and availability across retailers, to help you make confident purchasing decisions.

Amazon.Product.Search.mp4

Professional Talent Search

Efficiently discover and evaluate potential candidates based on skills, experience, and portfolio quality, creating detailed profiles for recruitment decision-making.

Finding.a.consultant.in.Upwork.mp4

Quick Roadmap

Features	Status
Multi-Agent Workflow	Completed
OpenAI LLM	Completed
Local LLM	In Progress
MCP	Planned
Customize Prompt in UI	Planned
Customize Agents in UI	Planned
Customize Workflow Graphs in UI	Planned
Eval Management	Planned
Memory	Planned
A2A Protocol	Planned

DevTools Documentation

• Agentic Framework Documentation
• Chromium Devtools Original Documentation

Agentic Framework Documentation

• front_end/panels/ai_chat/core/Readme.md: Explains how to customize the BaseOrchestratorAgent to add new top-level agent types and UI buttons, and details its graph-based workflow.
• front_end/panels/ai_chat/agent_framework/Readme.md: Describes the AI Agent Framework, its core components (ConfigurableAgentTool, AgentRunner, ToolRegistry), and how to create, configure, and register new custom agents, including agent handoff mechanisms.

Contributing

Found a bug 🐛 or have a feature idea ✨? Please create issues here

Join Us

If you like this project, don't hesitate to ⭐ star this repository. For those who'd like to contribute code or just hang out with the community please join our Discord.