An API for AI agents to search, scrape, and interact with web pages, returning clean markdown, JSON, and screenshots.
199.5K+2.1K this week10.5KTypeScriptAGPL-3.0Updated 5 hours ago
Agents & MCP
Browser automation for AI agents: 42 open-source projects (2026)
Let an AI agent click through websites, fill in forms and pull clean data from live pages.
- Project
- 42
- This week
- +11K
- Updated
- 3 hours ago
How to choose
Decide first what job you need done: pulling clean data from pages, or having an agent act inside a browser. For Markdown or JSON output, firecrawl/firecrawl is an API (AGPL-3.0, which matters for closed-source use), while unclecode/crawl4ai is an open-source Python crawler. For an agent that controls a real browser from Python, look at browser-use/browser-use. If your LLM client already speaks MCP, microsoft/playwright-mcp drives a browser through Playwright with little setup.
- firecrawlBest for developers who want an API that searches and scrapes pages and returns clean Markdown, JSON and screenshots.
- browser-useBest for Python developers building agents that control a real browser, with optional hosted stealth browsers.
- playwright-mcpBest for people whose LLM client supports MCP and who want browser control through Playwright and accessibility snapshots.
Top projects compared
| Project | Stars | This week | License | Updated |
|---|---|---|---|---|
| 199.5K | +2.1K | AGPL-3.0 | 5 hours ago | |
| 120.3K | +599 | MIT | 3 hours ago | |
| 87.1K | +403 | Apache-2.0 | 3 days ago | |
| 46.7K | +1.7K | Apache-2.0 | 3 hours ago | |
| 41.6K | +2.5K | AGPL-3.0 | 8 hours ago | |
| 39.3K | +402 | Apache-2.0 | 23 hours ago |
All projects
Open-source Python library for building AI agents that control a real browser, with optional Browser Use Cloud stealth browsers and hosted agent API.
120.3K+599 this week13.4KPythonMITUpdated 3 hours ago
Open-source Python web crawler that turns any website into clean, LLM-ready Markdown, with CSS/LLM-based structured extraction and an optional hosted API.
87.1K+403 this week9.1KPythonApache-2.0Well maintainedUpdated 3 days ago
Native Rust CLI that lets AI agents drive a Chrome browser through snapshots, element refs, and common automation commands.
46.7K+1.7K this week3.2KRustApache-2.0Updated 3 hours ago
A headless browser written in Zig from scratch for AI agents and automation, with CDP and WebDriver BiDi servers.
41.6K+2.5K this week2.1KZigAGPL-3.0Updated 8 hours ago
A Model Context Protocol server that lets LLM clients drive a real browser through Playwright using structured accessibility snapshots.
39.3K+402 this week3.4KTypeScriptApache-2.0Updated 23 hours ago
A Python web scraping library that uses LLMs and graph-based pipelines to extract structured data from websites and local documents based on a text prompt.
32.6K+206 this week3.3KPythonMITWell maintainedUpdated last month
A JavaScript library that embeds a GUI agent in any web page, letting users control the interface with natural language.
29.6K+36 this week2.6KTypeScriptMITUpdated 4 days ago
TypeScript, Python and Go SDK for browser agents that drives Chrome with natural-language act, observe and extract calls alongside Playwright-style APIs.
26K+88 this week1.8KTypeScriptMITUpdated 19 hours ago
Open-source browser automation that uses LLMs and computer vision to run web workflows on any site, extending Playwright with AI commands.
23.4K+37 this week2.2KPythonAGPL-3.0Updated 3 hours ago
A headless browser built in Rust for AI agents, offering CDP, WebDriver and BiDi automation with on-demand layout and rendering.
22.9K+1.1K this week639RustApache-2.0Well maintainedUpdated 3 hours ago
A browser built for AI agents and you to share: agents run tasks in isolated Spaces while your own tabs and logins stay untouched.
22K+1K this week1.2KJavaScriptMITUpdated 18 hours ago
Open-source web data platform that turns websites into structured APIs for scraping, crawling, search, monitoring and AI extraction.
18.2K+49 this week1.6KTypeScriptAGPL-3.0Updated 6 hours ago
An open-source Chromium-based browser built for AI agents, which runs locally and lets agents work in parallel tabs using your logged-in accounts.
14.3K+75 this week1.5KTypeScriptAGPL-3.0Updated 3 hours ago
Open-source Chrome/Edge extension where an AI agent runs in your own logged-in browser to carry out web tasks from a side panel.
14.3K+49 this week1.5KTypeScriptApache-2.0Well maintainedUpdated 15 days ago
A Go HTTP server that gives AI agents token-efficient control over Chrome, with multi-instance orchestration and a live dashboard.
10.6K+52 this week790GoMITWell maintainedUpdated 11 days ago
CLI and browser extension that let AI agents work in your logged-in Chrome or Edge while you keep using your browser.
10.2K+311 this week732TypeScriptMITWell maintainedUpdated 15 hours ago
A TypeScript framework that lets AI agents control a Playwright browser to autonomously complete web tasks like clicking, typing and extracting data.
9.6K+1 this week866TypeScriptMITUpdated 7 months ago
An Agent Skill that gives local AI agents like Claude Code full web access via tiered tool routing, a CDP browser proxy, and per-site experience notes.
9.4K+47 this week659JavaScriptNo licenseUpdated 24 days ago
Open-source browser API for AI agents and apps, running a managed Chrome sandbox you can drive with Puppeteer, Playwright, or Selenium.
7.9K+37 this week1KTypeScriptApache-2.0Well maintainedUpdated 3 days ago
A TypeScript library that uses LLMs to extract structured data from any webpage, built on Playwright and Zod or JSON Schema.
7K+2 this week451TypeScriptMITUpdated 13 days ago
Records browser interactions once and replays them as deterministic workflows, falling back to Browser Use AI when a step fails.
4.2K+5 this week356PythonAGPL-3.0Updated yesterday
An LLM-powered web scraper, built on Streamlit, that extracts data from pages using OpenAI, Gemini, Ollama or LiteLLM models.
3.3K360PythonMITUpdated 27 days ago
An Agent Skill that lets coding agents write and run custom Playwright browser automation scripts for tests and multi-step web tasks.
3.3K+12 this week255JavaScriptMITUpdated 7 days ago
A small Rust CLI that drives a real Chrome browser over the Chrome DevTools Protocol, designed for shell-based coding agents.
3.2K+4 this week210RustMITUpdated 2 months ago
An MCP server giving AI agents web search, page scraping, structured data extraction, and remote browser automation through Bright Data.
2.7K+16 this week337JavaScriptMITWell maintainedUpdated 2 days ago
Cloud browser infrastructure and a Playwright-based framework for running web automations with AI agents, with stealth, CAPTCHA solving and proxies.
2.1K+4 this week186PythonOtherUpdated 8 hours ago
Open-source AI browser agent extension for Chrome, Firefox and Edge that chats with pages and automates multi-step browser tasks using your choice of LLM.
1.7K+24 this week210JavaScriptOtherUpdated 4 hours ago
Builds MCP integrations for websites from a plain-language task, so AI agents can call sites that have no API.
1.6K+115 this week135TypeScriptMITUpdated 3 hours ago
A toolkit for extracting data and automating live websites with an AI-powered query language that works with Playwright, plus SDKs and a REST API.
1.5K+8 this week178PythonMITWell maintainedUpdated 4 days ago
FAQ
- How are these projects chosen?
- Every project on Repolode passes a quality screening before it is listed: it must be usable today, solve a concrete problem, be more than a thin wrapper and still be maintained. This page groups the listed projects by topic and ranks them by GitHub stars.
- Which project here is the most popular?
- firecrawl/firecrawl, with 199.5K GitHub stars. Check each project's license and last commit before choosing.