#4040th of 48 in Agent frameworks and SDKs

browseros

Secondary Chromium browser that AI coding agents drive over MCP with your logins

Documentation ↗ Website ↗ Repository on GitHub ↗

Stars: 13.8k
License: AGPL-3.0
Last commit: Oct 2026
Last release: Oct 2026
Language: TypeScript

Missed the latest GitHub check; these facts may be older.

Overview

BrowserOS neo is a Chromium-based browser that sits next to Chrome and exposes an MCP endpoint on 127.0.0.1, so agents such as Claude Code, Codex and Cursor can run web tasks in your logged-in sessions. It imports logins, bookmarks and extensions from Chrome, runs agents in parallel tabs, and saves each session as a replayable video with an action timeline. The repo also ships BrowserOS, a separate Chromium fork with a built-in agent.

Who it is for: Developers who want coding agents to automate logged-in web tasks locally

Strengths

Imports Chrome logins, bookmarks and extensions in one click, so agents use real accounts
Works with any MCP client; one-click connect for Claude Code, Codex, Cursor, VS Code and others
Sessions saved locally as scrubbable video with step-by-step action timeline
Runs on 127.0.0.1 with local-only session data under ~/.browserclaw/

Weaknesses

Linux builds are x64 only
Sends anonymous usage events by default; opt-out via a Settings toggle
Not a Chrome replacement; needs a separate agent harness to issue tasks
AGPL-3.0 license may restrict some commercial or embedded use

What it needs

no GPU
Needs MCP-compatible agent (Claude Code, Codex, Cursor, etc.)
Models: Any MCP client, Claude Code, Codex, Cursor, Ollama (BrowserOS only)

Also in Agent frameworks and SDKs

See all 48

Also in Agent frameworks and SDKs
Rank	Project	Score
1	ppt-masterAgent skill that turns documents into natively editable PowerPoint decks Live demo ↗ (opens in a new tab)62.1k starsMIT	93 out of 100
2	browser-usePython library that lets an LLM agent control a web browser Live demo ↗ (opens in a new tab)118k starsMIT	89 out of 100
3	langchainPython framework for building LLM agents and apps from interoperable components147.8k starsMIT	88 out of 100
#4	tradingagentsLangGraph multi-agent framework simulating a trading firm to analyze tickers Live demo ↗ (opens in a new tab)111.2k starsApache-2.0	88 out of 100
#5	copilotkitSDK for adding agent chat, generative UI and shared state to apps38k starsMIT	87 out of 100

How to choose

Pick by language first (Python or TypeScript), then by how much the framework hides.
Check how it handles tool errors and retries; that is where agents break in production.
Look for tracing hooks so you can see each step later.

Health

Releases: Not checked
Top contributor: Not checked
Security advisories: Not checked
Package advisories: Not checked
OpenSSF Scorecard: Not checked

Not read for this project yet: each refresh reads the facts of a few projects. Bots and coding-agent accounts are left out of the commit counts. Not part of the score: how we check.

License in plain words

AGPL-3.0 Copyleft

Use it at work: Yes
Change it and rebrand it: Yes
Sell it or host it for others: Yes, with source

Your part: Like GPL-3.0, and if users reach a changed version over a network, offer them its source under AGPL-3.0.

A plain summary, not legal advice. Read the license on GitHub ↗ (opens in a new tab)

#40 of 48 in Agent frameworks and SDKs on Archestack, as of 15 Oct 2026.

In your README

The badge updates twice a day.

[![Archestack](https://archestack.com/badge/browseros-ai/browseros.svg)](https://archestack.com/best-of-ai/projects/browseros/)

How badges work

On your site or blog

A card with the rank, score and signals, in light or dark to match the reader.

<iframe src="https://archestack.com/embed/best-of-ai/browseros/" title="browseros on Archestack" width="400" height="270" style="border:0;max-width:100%" loading="lazy"></iframe>

Preview the card

Best of Open-Source AI on GitHub

Each review comes from the project's README and facts we check on GitHub. The fix form opens with browseros filled in.