chrome-agent: Direct CDP Control for AI Coding Agents

Repositorycaptivus/chrome-agentTool

chrome-agent is a CLI tool and Python library giving AI coding agents direct browser inspection and interaction via the Chrome DevTools Protocol (CDP). It avoids restrictive abstraction layers and enables concurrent, isolated use by multiple agents and human operators.

Key points

  1. Full CDP access: Provides unrestricted control over all Chrome domains, methods, and events without being constrained by a curated tool wrapper.
  2. Shared browser sessions: Multiple agents and human developers can operate against the same browser instance concurrently with isolated event streams.
  3. Schema-agnostic passthrough: Commands and parameters are routed directly to Chrome, allowing newly added CDP domains (such as CrashReportContext or WebMCP) to work immediately without updating the CLI.
  4. Live documentation: The built-in help command queries the active browser instance to read the current protocol schema.
  5. Package installation: Available via PyPI and installable directly using uv (e.g. uv tool install chrome-agent).

Why it matters

Typical browser MCP setups rely on persistent servers with heavy abstraction and verbose output. chrome-agent allows coding agents to interact with web pages natively at the protocol level, mirroring how DevTools operates for human developers.

Analysis

With 243 GitHub stars and an MIT licence, the project represents an emerging, focused alternative to conventional MCP browser abstractions. Its direct pass-through design prevents obsolescence against Chrome updates, though it relies on LLMs knowing or discovering correct CDP primitives.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Repository:ChromeDevTools/chrome-devtools-mcp

    Chrome DevTools MCP: Browser Debugging and Performance Analysis for Coding Agents

    chrome-devtools-mcp connects AI coding agents to Google Chrome via the Model Context Protocol (MCP). It enables agents to automate browser actions using Puppeteer, inspect network traffic and console errors with source maps, and collect detailed performance traces.

    50.8kstarsTypeScript

    AI & LLMs· Tool

  • Repository:FeiZhuLulu/Agent-Bridge

    Agent Bridge: Orchestrating Local Coding Agents via MCP

    Agent Bridge is an open-source Python tool connecting local coding agents using the Model Context Protocol (MCP). It allows users to interact with a single coordinator agent that delegates tasks to multiple specialized CLI worker agents.

    31starsPython

    AI & LLMs· Tool

  • Video

    Video:AI Engineer

    Web Automation with AI Agents via the Chrome DevTools Protocol

    Corey Gallon demonstrates how AI agents can bypass modern bot detection systems like Cloudflare Turnstile and reCAPTCHA using the Chrome DevTools Protocol (CDP). By combining deterministic execution with targeted vision calls and human-like mouse dynamics, agents interact with browsers indistinguishably from human users.

    AI & LLMs· Talk

  • Repository:citrolabs/ego-lite

    ego lite: A Browser Designed for Shared Use Between Humans and AI Agents

    ego lite is an open-source browser built for macOS that allows users to share their active logged-in sessions with AI agents such as Claude Code or Codex. It isolates agent automation tasks into dedicated Spaces, enabling background execution without disrupting the user's open tabs.

    15.1kstarsJavaScript

    AI & LLMs· Tool

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.