AgentToolDrop

15 of 57

ego lite

Browser where agents work in their own Spaces with your migrated Chrome logins while you keep browsing

  • score 54
  • 17.6k stars
  • 95.2 stars/day since creation
  • pushed
  • v2.1.0 on
  • MIT

Add the ego-browser skill with npx

npx skills add citrolabs/ego-lite

Copied from the project's docs at github.com/citrolabs/ego-lite

Why you'd want it

ego lite is a browser where each agent runs its browser tasks in its own Space, an isolated workspace inside the same browser, while you keep browsing in yours. On first launch it asks whether to migrate your Chrome data, and saying yes lets the agent inherit your existing logins, cookies, extensions and bookmarks. The ego-browser skill connects agent CLIs such as Claude Code, Codex or Cursor to the browser, exposing snapshot, fill, click, wait, navigate and capture as in-page JavaScript tools that the agent calls from one script. The README reports that it finished four complex tasks up to 2.5x faster than Vercel's agent-browser, which is the vendor's own benchmark.

Best for

  • Agent tasks behind your existing logins
  • Several agents working in parallel Spaces
  • Browser automation without losing your own tabs

Use it when

You want Claude Code, Codex or Cursor to do browser tasks on macOS using your existing logins, without the agent taking over the browser you are using.

Skip it if

You are not on macOS; the README says it runs on macOS today, with a Windows closed beta coming soon and Linux on the roadmap. Migrating your Chrome data gives the agent your logins and cookies, so it can act as you on those sites and runs JavaScript it writes on the pages it opens; the README says you can take over or stop a Space at any time, so migrate only data you are comfortable exposing to an agent. It also needs the ego lite browser app; the README says the repo contents are MIT and the browser is a separate, free download, so the browser itself is not covered by that license.

Editor's note

The README says the skill walks you through installing the macOS app the first time an agent runs a browser task; you can also download the .dmg or paste its agent setup prompt. The speed and comparison-table claims are the vendor's own and were not tested here.

Related tools

Same category or shared tags.

  1. Rank 38

    Browser Harness

    Browser agent

    Lets Claude Code, Codex or Cursor drive your own Chrome over CDP, logged in as you

    • score 38
    • 18.5k stars
    • 9.8 stars/day last 3 days
    • pushed
    • v0.1.13 on
    • MIT

    Install with uv

    uv tool install --python 3.12 --upgrade --force browser-harness
    Use it when, skip it if, stats for Browser Harness

    Why you'd want it

    Browser Harness connects a coding agent to your running Chrome through the DevTools Protocol, so it can open pages, click, type, read and download with your existing logins. It installs as a CLI with a skill that teaches the browser workflow, and the agent writes missing helpers into its local workspace as it works while the core package stays protected. A browser-harness-mcp command exposes the same helpers as MCP tools for any MCP client.

    Best for

    • Logged-in web tasks from a coding agent
    • Claude Code, Codex and Cursor
    • MCP clients that need a real browser

    Use it when

    You want your coding agent to work in the browser where you are already signed in, instead of a fresh headless profile.

    Skip it if

    You do not want an agent acting in your real, logged-in browser profile: setup turns on Chrome remote debugging, and the agent acts as you on the sites you use. Optional local recordings save screenshots and action traces that may include sensitive page content.

    Stats

    New and rising score
    38 of 100
    Stars per day, last 3 days
    9.8
    Release
    v0.1.13,
    License
    MIT
    Pricing
    Open source
    Works with
    Claude Code, Codex, Cursor, Any MCP client
    Forks
    1,902
    Open issues
    411
    GitHub checked

    Full stat block for Browser Harness

  2. Browser Use

    Browser agent Standard

    Lets an LLM drive a real browser to complete multi-step web tasks from Python code or a CLI

    • 118k stars
    • 110 stars/day last 3 days
    • pushed
    • 0.13.13 on
    • MIT

    Install with uv

    uv add browser-use
    Use it when, skip it if, stats for Browser Use

    Why you'd want it

    Browser Use is an open-source browser agent: you give it a task in plain language and a model, and it opens a browser, works through the site and returns a result. It works with OpenAI, Anthropic and Google models or local models through Ollama, accepts custom tools registered as Python functions, and can drive a local Chrome profile, a remote browser over CDP or a Browser Use Cloud browser. A CLI gives existing agents such as Claude Code, Codex and Cursor browser access, and an integration implements Claude's browser toolset with Browser Use as the driver.

    Best for

    • Python apps that automate tasks on real websites
    • Giving a coding agent browser access
    • Projects that may move to hosted browsers later

    Use it when

    You want an agent that completes tasks on live websites, such as forms, bookings and lookups, from your own Python code with your choice of model.

    Skip it if

    You only need fixed, scripted browser steps with no model in the loop. The library needs Python 3.11 or later, and stealth browsers, proxies and the BU2 model are paid Browser Use Cloud services.

    Stats

    Stars per day, last 3 days
    110
    Release
    0.13.13,
    License
    MIT
    Pricing
    Open source
    Works with
    Claude Code, Codex, Cursor
    Forks
    13,130
    Open issues
    562
    GitHub checked

    Full stat block for Browser Use

  3. Rank 39

    agent-desktop

    Browser agent

    Gives an agent a CLI that reads and operates macOS apps through their accessibility trees

    • score 38
    • 1.8k stars
    • 3.4 stars/day last 3 days
    • pushed
    • v0.10.1 on
    • Apache-2.0

    Install with npm

    npm install -g agent-desktop        # downloads prebuilt binary automatically
    Use it when, skip it if, stats for agent-desktop

    Why you'd want it

    agent-desktop is a Rust CLI that snapshots an app's accessibility tree into compact element references, which the agent then uses to click, type, scroll and manage windows. A skeleton mode returns a shallow overview of dense apps such as Slack and lets the agent drill into one region, and commands return structured JSON with error codes and recovery hints. Sessions record traces that export to a single HTML viewer, and launch --cdp opens a DevTools port on Chromium-based apps so Playwright or Puppeteer can drive the web contents.

    Best for

    • Agent control of native Mac apps
    • Compact UI snapshots of dense apps
    • Calling from Python, Swift or Node through its C library

    Use it when

    You want a shell-driven agent to operate Mac apps by element reference instead of guessing coordinates from screenshots.

    Skip it if

    You are on Windows or Linux, which the README lists as planned. It needs macOS Accessibility permission, plus Screen Recording for screenshots, and can click, type and use the clipboard in any app it is pointed at.

    Stats

    New and rising score
    38 of 100
    Stars per day, last 3 days
    3.4
    Release
    v0.10.1,
    License
    Apache-2.0
    Pricing
    Open source
    Works with
    macOS
    Forks
    129
    Open issues
    6
    GitHub checked

    Full stat block for agent-desktop

For agents

The same entry, as files an agent can read without scraping this page. 

# read one entry
curl -s https://agenttooldrop.com/tools/ego-lite.md

# list the MCP servers in the catalog
curl -s https://agenttooldrop.com/tools.json \
  | jq -r '.tools[] | select(.category=="mcp-server") | .slug'