Automation and scraping

Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥

199,902 stars+1,906 this week

👾 Open Computer Use – Open-Source Alternative to Codex Computer Use

2,900 stars+75 this week

Fast, lightweight Firecrawl/Tavily alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Firecrawl-compatible API (/scrape, /crawl, /search). 2.3x faster than Tavily, 1.5x faster than Firecrawl in 1K-URL benchmarks. 6 MB RAM, single binary. Self-host or use managed cloud.

1,237 stars+26 this week

Native Linux desktop control for AI agents (MCP, Pi, CLI): semantic AT-SPI trees, screenshots, window targeting, and input across GNOME, KDE, Hyprland, niri, COSMIC, i3, Sway, labwc and other wlroots compositors, and X11.

831 stars+45 this week

Self-learning agent browser

2,768 stars+13 this week

Codex computer use, decoupled from the app, for usage inside any harness.

2,398 stars+35 this week

Free, open-source anti-detect browser launcher for web scraping and multi-accounting. By the ShardX team (formerly ProxyShard). Engine-level fingerprint spoofing in Chromium 157 (WebGL / WebGPU / Client Hints / fonts / TLS), 220+ device profiles bundled, stable QUIC + WebRTC over SOCKS5.

1,463 stars+76 this week

nanoMuse: an open-source personal agent for every device you own. One agent with a name and a look of its own that does things, keeps working while the app is closed, remembers you, and asks before anything you cannot undo. On Android, iPhone and iPad, Windows / macOS / Linux and in the browser; your phone's screen and your computer as its hands.

3,341 stars+264 this week

Make Any Website into CLI & Use your logged-in browser by AI agent.

30,974 stars+150 this week

OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks

412 stars+7 this week

Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.

1,294 stars+14 this week

Boss直聘爬虫 / BOSS直聘职位数据抓取工具，基于 Chrome CDP 协议复用真实登录态，绕过字体反爬，输出明文薪资 JSON/CSV + 薪资技能分析。A Chrome-CDP-based BOSS Zhipin job scraper/crawler.

1,729 stars+43 this week

DeepSeek Harness的Windows电脑操控插件 / Windows computer use for DeepSeek Harness

605 stars+151 this week

A fast browser agent: Jev picks each action from what is on the page, an LLM reads and plans, and every claim in an answer cites a quote from the page.

220 stars+49 this week

Open-source stealth Chromium with engine-level fingerprint spoofing - de-Googled, drop-in Playwright, fully buildable and verifiable from source.

248 stars+12 this week

Open-source, local-first social media research agent for Instagram, TikTok, and LinkedIn. Jev routes read-only steps; socai CLI captures cited browser evidence.

207 stars+13 this week

An on-device LLM understands your entire life, then proactively offers to get your work done through computer use.

716 stars+23 this week

Playwright MCP server undetected by anti-bots and captchas: AI agent browses the web on anti-detect stealth Firefox, Python, undetected browser automation, scraping, computer use.

877 stars+14 this week

ODS V3 Pre-Release: Public testing and refinement ahead of the official V3 launch. Turn your PC, Mac, or Linux box into a private AI server.

7,801 stars+56 this week

Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.

120,380 stars+543 this week

Official Crawl4AI Cloud: a hosted web scraping, extraction, and search API for AI agents. Free API key, 1,000 credits a month, no card. Fully open source: this repo is the Apache-2.0 crawler that powers it, and you can self-host it.

87,122 stars+346 this week

The SDK to extract data and interact with any site on the web. Get started with Claude Code, Codex, Eve, Mastra, and more.

25,988 stars+82 this week

Stealth Chromium that passes every bot detection test. Drop-in Playwright replacement with source-level fingerprint patches. 50+ tests passed.

32,787 stars+113 this week

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

418 stars+9 this week

🚀 自托管的抖音、TikTok、B 站数据采集与无水印视频下载 API，支持 AI agent 通过 MCP 调用与离线语音转文字，Docker 一键部署。| Self-hosted TikTok, Douyin & Bilibili scraper and no-watermark video downloader — async REST API, MCP server for AI agents, CLI and web console, plus offline speech-to-text for downloaded videos. Self-healing identity pool, PostgreSQL archive, one docker compose up.

21,301 stars+202 this week

Always-on AI Gods that work inside Claude Code, and you can talk to them. Proactive workers, computer use (browser, terminal & files), real-time voice like Jarvis, workers on a call in their own voice, Slack, and Spaces for your projects.

51 stars+2 this week

让任何 AI agent 操控你自己的 Chrome——带着全部登录态。MCP + Chrome 扩展，Claude Code / Codex / Cursor / Gemini CLI 通用。

579 starsThis week: Not stated

Local-first AI agent for Chrome: browser automation, web research, and data extraction with your own model.

213 stars+48 this week

Search and read the web for AI agents at 99% fewer tokens. Free CLI + MCP.

131 stars+79 this week

Scout: the open-source browser agent, by Outcrawl. Mirrored automatically from Outcrawl's own repository.

743 stars+3 this week

Stealth Chromium browser for web scraping and AI agents.

214 starsThis week: Not stated

Can AI agents rebuild websites through browser exploration?

144 stars+121 this week

Self-hosted web scraper, crawler and document parser for AI agents: URLs, PDFs with OCR and Office files to clean Markdown/JSON. Firecrawl- and Jina-compatible API, MCP server, agent endpoint, Python/Node SDKs. Single Rust binary.

255 stars+68 this week

Let Claude Code, Codex or Cursor use your real Chrome, logged in as you. One prompt to set up. Open source, MIT.

18,965 stars+142 this week

Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML

7,103 stars+43 this week

Python scraper based on AI

32,645 stars+213 this week

源码级 Chromium 指纹内核，检测站按普通 Chrome 评分。Source-level Chromium fingerprint kernel that passes bot detection tests. Not JS injection — C++ patches compiled into the binary.

1,125 stars+75 this week

For EHRs, payer portals, and any app your team clicks through. A person or an agent shows the task; OpenAdapt turns it into a local program that repeats the steps with no model calls, checks each save, and stops when something doesn't match.

1,869 stars+9 this week

One read() call for AI agents, stitched from 41 web tools.

110 stars+2 this week

System 1 decision models (Jev, Laya, Cua-S1) as brain for agents: Browser use, computer use, games and robotics

181 stars+2 this week

Automate browser based workflows with AI

23,367 stars+49 this week

A Fully free agentic browser driver for AI , few tools, full control, real stealth, top-tier token efficiency.

344 stars+4 this week

Self-hosted Google search scraper for Python. Scrape Google SERP results with a real Chrome browser and your own residential proxy. Self-hosted SERP API alternative with JSON output, an HTTP API and an MCP server for AI agents.

113 stars+9 this week

Agent-native browser with fingerprint control and proxy support.

138 stars+2 this week

🔥 Open Source Browser API for AI Agents & Apps. Steel Browser is a batteries-included browser sandbox that lets you automate the web without worrying about infrastructure.

7,939 stars+31 this week

AI computer use powered by open source LLMs and E2B Desktop Sandbox

2,407 stars+13 this week

Assistant vocal local en francais : Claude ou Ollama (offline), domotique Hue, OBS, agenda, navigateur, appels Twilio, serveur MCP. Python.

549 stars+6 this week

Free, open-source anti-detect browser profile manager: per-profile fingerprint, cookies and proxy, Camoufox and Chrome engines, desktop app, REST API and MCP server for AI agents. Self-hosted alternative to GoLogin / MoreLogin.

189 stars+6 this week

A Chrome side-panel agent for your signed-in browser. Read pages, take action, create files, and run local follow-ups. Bring your own models.

2,383 stars+4 this week

Browser automation where an LLM plans and Jev (Typesafe System One) decides. Library, CLI and MCP server.

132 stars+4 this week

JavaScript in-page GUI agent. Control web interfaces with natural language.

29,650 stars+35 this week

The open-source agent harness, ready out of the box and customizable in depth. Tools, context, durable execution, permissions and recovery for code, research and office work, with a long-running super-agent Bot that leads a team of agents.

142 stars+70 this week

Open-source desktop AI agent that takes real actions on websites — 33 adapters for mail, shopping, social, and more.

200 stars+42 this week

Agent S: the state-of-the-art open source computer use agents

12,911 stars+53 this week

🚀🚀 A multimodal System One decision model that gives calibrated answers to typed questions about screens, photos, video and text in one forward pass.

251 stars+32 this week

Give your AI agent a real browser — with a human in the loop. Open-source MCP-native browser agent.

924 stars+7 this week

Turn any website into a compact CLI tailored for AI agents. Browse the web in hundreds of tokens, not tens of thousands.

551 stars+4 this week

Open-source AI agent for web automation. Use your real, logged-in browser to automate daily tasks.

14,265 stars+44 this week

Residential, datacenter, ISP & mobile proxies with 90M+ IPs in 200+ countries — plus Scraper & SERP APIs. Code examples in Python, Node.js, PHP, Go, Java, C#, Ruby and curl.

778 stars-1 this week

Browser automation, web scraping, and testing. CDP Mode provides a Stealthy Chromium instance that bypasses bot-detection systems. Includes an MCP server.

13,233 stars+19 this week

Anti-detection browser server for AI agents — REST API wrapping Camoufox engine with OpenClaw plugin support

438 stars+3 this week

Automated CAPTCHA solver for your browser. Works with Selenium, Puppeteer, Playwright, and more.

11,099 stars+16 this week

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

39,583 stars+71 this week

An agent-native QA CLI for web pages. Deterministic, no tests to write, no LLM.

110 stars+1 this week

Go web crawler to scrape documentation sites and convert content to clean Markdown for LLM ingestion (RAG, training data)

109 stars+1 this week

Agent-Sandbox is an easy-to-use, enterprise-grade sandbox platform for AI Agents — letting them securely run untrusted LLM-generated code, Browser use, Computer use, and deploy websites, among other tasks.

231 stars+2 this week

The self-hosted AI workflow automation platform for Git repositories.

196 stars+2 this week

Self-hosted flight, hotel, and car rental price tracking with alerts, price history, and web and CLI interfaces.

185 stars+3 this week

Say it, and your Mac does it. A computer-use harness on Jev that reads the screen through Accessibility. Fast, no vision model

130 stars+1 this week

Open-source AI browser agent — type plain-language commands and Bah operates the web for you. Works with cloud AI (DeepSeek, Mistral, NVIDIA) or local Ollama models.

108 stars+1 this week

Turn any website into clean, structured data: Markdown, metadata and links from one page or a whole site, in every major language.

196 stars+1 this week

AIPex: AI browser automation assistant, no migration and privacy first. Alternative to Manus Browser Operator、 Claude Chrome and Agent Browser

1,283 stars+4 this week

A Smart, Automatic, Fast and Lightweight Web Scraper for Python

8,080 stars+10 this week

Self-hosted message gateway for AI agents: Codex, QQ, WeChat/WeCom, Feishu, smart devices and desktop automation. | AI 消息网关：连接聊天、智能设备与 Agent，支持定时任务和角色上下文。

492 stars0 this week

An advanced, high-performance Python client, MCP server, and REST API for reverse-engineering Perplexity AI's WebUI.

142 stars+2 this week

Lightweight scraper for Google News

384 stars0 this week

A skill for AI agents: search the web with SearXNG, browse with Camofox, bypass protections with CloakBrowser. Anti-hallucination by design. Self-hosted, free, unlimited.

543 stars+4 this week

DOM-first AI browser automation for Chrome and MCP clients.

205 stars+1 this week

Autonomous web browser agent that audits performance, functionality & UX for engineers and vibe-coding creators. 网站自主评估测试 Agent，支持 GUI/CLI 一键完成性能、功能使用与交互体验的测试评估

240 stars0 this week

One call where Aside used to spend fifty — rg-backed search, Aside-shaped file tools, and batched browser work inside a single sandboxed JavaScript block. On a real folder, 55s of find+grep became 1s.

129 stars0 this week

One command for every interface—search, run, and inspect real software across APIs, browsers, desktops, local tools, and MCP.

228 stars0 this week

AI-powered StartUp Accelerator Engine built with Next.js, LangChain, PostgreSQL + pgvector. Upload, organize, and chat with documents. Includes predictive missing-document detection, role-based workflows, and page-level insight extraction.

896 stars+2 this week

AI-native web scraper. Single binary with a bundled Claude Code skill. MIT-licensed alternative to Firecrawl.

152 stars0 this week

Browser automation clicks buttons. OpenTabs calls APIs.

1,017 stars+9 this week

This is the official website for TuriX Computer-use-Agent

3,176 stars+1 this week

Simplify Web Reverse-engineering for AI Agents

179 stars+1 this week

Browser automation plugin for OpenCode AI editor - Control Chrome/Edge with AI, automate web testing, scraping & form filling via MCP integration

114 stars+1 this week

Open source web infrastructure for AI. Scrape, crawl, and automate the web, clean markdown, browser sessions, ready for your agents.

562 stars+1 this week

A Powerful web scraper powered by LLM | OpenAI, Gemini & Ollama

3,298 stars-1 this week

WebAI2API: 基于 Camoufox 的网页 AI 转 API 工具，支持 LMArena/Gemini等，多窗口并发与账号隔离。 | Web AI to OpenAI API via Camoufox. Supports LMArena/Gemini and more, multi-window concurrency & account isolation.

1,424 stars+6 this week

Web-Use is a CDP powered Browser Agent

303 stars+2 this week

Modular AI agent workflow automation platform with schedulers, tools, and observability. https://vmdeshpande.github.io/ai-automation-platform-website/

178 stars0 this week

Agent-ready Amazon Scraper API: real-time product details (batch ASIN), offers & stock, reviews, search, best sellers, deals and seller data across 20 marketplaces. One pasted line for Claude Code / Codex / Cursor, an MCP server, or plain HTTP with 3 free calls a day and no key. Python examples inside.

227 stars+1 this week

Anti-detect browser automation CLI & Skills for AI agents — Camoufox-powered fingerprint spoofing, no bot-detectable Playwright leaks

360 stars+2 this week

Drive your real Chrome from any AI agent — logged-in sessions, real fingerprint, live tabs. CLI-based, works with OpenCode, Pi, or any Harness.

114 stars0 this week

A self-healing scraper for hostile sites: broken selectors repair themselves, browser rendering kicks in when needed, and a coherent identity layer (Chrome TLS fingerprints, matched personas, vendor-aware Cloudflare/Akamai/DataDome handling) works to slip past bot detection. Ships with an MCP server so any LLM can drive a full crawl by conversation.

117 stars0 this week

Extract information from all games published in Steam thanks to its Web API, and store it in JSON format.

167 stars+2 this week

Turn Webpage to LLM friendly input text. Similar to Firecrawl and Jina Reader API. Makes RAG, AI web scraping, image & webpage links extraction easy.

315 stars+1 this week

Turn any webpage into structured data using LLMs

6,953 stars+4 this week

A multithreaded 🕸️ web crawler that recursively crawls a website and creates a 🔽 markdown file for each page, designed for LLM RAG

480 stars+1 this week

Teach AI how your work actually gets done. Capture real computer work, extract the workflow graph and judgment, then run it with Codex or your own agent.

175 stars0 this week

Open‑source alternative to Perplexity Comet, director.ai and firecrawl combined

180 stars0 this week

Local-first Canvas LMS AI agent that learns each course's recurring assignment workflow and reuses it through scan -> approval -> execute with student review.

125 stars0 this week

Open workflow intelligence for discovering, validating, repairing, and generating automation workflows across frameworks — starting with n8n.

557 stars0 this week

A swarm of disposable agents for unattributable web interaction

414 stars-3 this week

wxpath - declarative web crawling with XPath; a Web Query Language (WQL)

110 stars0 this week