Browser Automation Listings
Compare the best open-source listings for browser automation. Agents that drive real browsers. Ranked by GitHub stars, with install commands, what each one can touch and scan reports where available.
Browser Use Vision
Vision-grounding plugin for browser-use agents with SoM, Florence-2, Vision–DOM alignment, adaptive visual context, and objective evaluation.
Aside Jev
Aside agents decide with TypeSafe Jev (System One: Choice/Score/Noul). Not a Cua binding — Jev is the model, Aside is the browser runtime.
Browser Pool
Session management library for Playwright remote browsers. Handles pooling, health checks, and auto-recovery for high-frequency scraping.
Edge Browser Agent
Small local models on Android phones operate real desktop browsers through the E2LLM/SiFR perception layer. Newest: Ministral 3 3B on a Galaxy S21 relays a live conversation between Gemini in Chrome and Z.ai in Firefox, 10/10 runs. Verified tasks, raw-HTML control, full JSONL logs, offline replay.
AI Web
AI Web:面向 Web 自动化测试的自然语言 Browser Agent 执行平台,支持多浏览器调度、任务队列与可追溯报告。
Autono
⚡ Autonomous AI Browser Agent & Navigation Copilot (Manifest V3) with Google Gemini, Anthropic Claude & OpenAI
Laya Ultrafast
Local browser AI agent with indexed action space — Laya local decisions, /opt/homebrew/bin/bash/run. Google Flights demo in ~6.5s. Python.
Browsertrace
Local replay debugger for Browser Use failures with screenshots, model I/O, failed-step timelines, and public-safe HTML exports.
Resurf
A deterministic, reproducible test environment for AI browser agents
OpenSidebar
Agentic Browser Extension
CloakBrowser Agent
Jev-powered stealth browser agent. TypeSafe Jev decides each step in ~0.3 s, CloakBrowser carries it out like a human. MCP server, CLI and Python API.
Myna Browser Agent
An open-source alternative to Claude in Chrome. Bring your own API key and let an AI agent read, click, fill, and research across tabs. No account, no backend, no telemetry.
List refreshed November 15, 2026. Data comes from public GitHub repositories.