Browser Use Python Packages

browser-use

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

smolvm-core

Open-source AI sandbox infrastructure for code execution, browser use, and AI agents.

taprun

Local-first browser automation MCP for Claude Code / Cursor. taprun compiles once with AI, your authenticated Chrome replays forever at zero LLM tokens. Credentials never leave your machine.

open-browser-use-sdk

🔮 Platform-neutral Browser Use for AI agents: real Chrome automation with a CLI + SDKs, no lock-in, dead simple.

vibesurf

A powerful browser assistant for vibe surfing 一个开源的AI浏览器智能助手

clawbench-eval

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

browsertrace

Local replay debugger for Browser Use failures with screenshots, model I/O, failed-step timelines, and public-safe HTML exports.

minitap-mobile-use

AI agents can now use real Android and iOS apps, just like a human.

wraith-mcp

AI-native stealth browser MCP server — Browser Use + Patchright

magentic-ui

A research prototype of a human-centered web agent

browser-use-undetected

Undetected browser automation addon for browser-use with proxy support

clawbenchmark

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

minitap-mcp

AI agents can now use real Android and iOS apps, just like a human.

optexity-browser-use

Make websites accessible for AI agents

unbrowse-hermes

Unbrowse — api native browser MCP/SDK for any agent. Auto-discovers APIs from browser traffic, generates skills on the fly to call APIs directly 100x faster, 80% cheaper locally.

clawbench-harness

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

claw-harness

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

nail-clawbench

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

cesail

CeSail provides a fully-featured AI agent and platform for automating web tasks. Agents can interact with websites autonomously, parse complex DOM structures, and extract structured, agent-friendly data. With CeSail, you can automate browsing, data collection, and web interactions reliably and efficiently.

openclawbench

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

clawbench-cli

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

auth-agent-sdk

Official Python SDK for Auth Agent - OAuth 2.1 authentication for websites and AI agents. Includes client SDK for Python backends (Flask/FastAPI) and agent SDK for browser automation with browser-use integration.

usewitness

Local-first observability for browser agents. See what your agent actually did.

tn-browser-use

Make websites accessible for AI agents