Directory
Browser automation
Reviewed resources in Browser automation. 88 resources listed.
FSB (Full Self Browsing)
full-selfbrowsing.comAn open-source Chrome extension that reads a page's DOM to plan and carry out browser automation from a plain-English instruction, for interactive use and MCP clients.
nuphus-mcp
github.comA lightweight, cross-platform MCP server that exposes desktop and Chrome browser automation as standard tools, letting any MCP client control the screen, windows, mouse, keyboard, and Chrome over stdio JSON-RPC.
Open Browser Use
ifuryst.comA platform-neutral browser automation layer for AI agents that pairs a Chrome extension with a CLI, JavaScript, Python, and Go SDKs, and an MCP server for driving real Chrome sessions.
Kane CLI
testmuai.comA command-line tool that turns a plain-English objective into a real Chrome browser automation run and returns structured results, used both as a standalone browser automation CLI and as a validation layer AI coding agents call to check their own work in a real browser.
RA Browser Use
github.comA Chrome browser-automation agent, forked from Nanobrowser, that runs its model on-device inside the extension by default, so a task in plain language runs with no API key, no cloud call and no page content leaving the browser.
OmniAct
github.comA lightweight, cross-environment general-action agent that completes real digital tasks spanning a browser, desktop applications and the command line, coordinated by a TeamLeader that dispatches to specialized Workers.
PullMD
github.comA self-hosted service that converts a web URL, or as of v3 a PDF, Office document, EPUB, image, audio file or YouTube video, into clean Markdown for humans and AI agents to read.
DrissionPage MCP Server
github.comAn MCP server that exposes DrissionPage's Chromium/CDP browser automation as 69 typed, atomic tools for Claude Code, Codex and other MCP clients, including deterministic mouse-motion profiles.
h5i
h5i.devAn agent-native workspace for red-teaming web applications that combines a fast browser with direct control over HTTP traffic, so agents can navigate, capture, inspect, modify, replay and compare requests in one sandboxed, auditable interface.
dsh-antibrow
antibrow.comA DeepSeek Harness plugin that gives an agent a persistent browser identity: a Chromium fork with engine-level fingerprint spoofing, saved profiles and logins between runs, Android device emulation, and residential proxy egress.
dsh Browser Control
github.comA Chrome and Firefox sidebar extension that lets DeepSeek's DSH agent harness read and operate a user's own browser tabs as structured text, preserving login sessions and cookies without ever taking a screenshot.
fastCRW
fastcrw.comA Rust command-line tool and API that turns URLs into clean markdown or structured JSON for search, scrape, map, crawl and extract operations, runnable locally or through a managed cloud service.
ClawBench: Can AI Agents Complete Everyday Online Tasks?
claw-bench.comAn open-source benchmark that evaluates browser AI agents on everyday online tasks such as booking travel, ordering food and applying for jobs, across a set of live websites.
WebBrain
webbrain.oneWebBrain is an open-source browser extension that adds an AI agent to a side panel in Chrome or Firefox, so it can answer questions about the page you're on or carry out multi-step browsing tasks using a model you choose.
Browser4
browser4.ioAn AI-native browser automation engine for autonomous agents, offering both zero-token deterministic extraction and LLM-driven extraction at large scale, controlled by a Rust CLI and MCP.
A Chrome extension that runs an on-device AI assistant entirely in the browser with WebGPU and Transformers.js, letting it manage tabs and answer questions about the current page.
Stealth Browser MCP
github.comAn MCP server that gives AI agents stealth browser automation for getting past Cloudflare challenges, anti-bot checks and login walls, using real Chrome-family browser instances.
Notte
notte.ccA framework and hosted API for building AI agents that operate on websites, combining scripted automation with AI so routine steps run as code and models are used only where judgment is needed.
webclaw
webclaw.ioA Rust-based, local-first web content extraction tool that turns a URL into clean Markdown, JSON or other LLM-ready output for AI agents and RAG pipelines, available as a CLI, an MCP server, a REST API and a self-hostable server.
Apify Agent Skills
skills.shA collection of Agent Skills giving an AI coding assistant expert use of the Apify web-scraping platform: selecting from more than 130 curated scraping Actors, building and deploying new Actors, wrapping existing code as an Actor, and generating an Actor's input/output schemas.
hCaptcha Challenger
github.comAn open-source tool that solves hCaptcha challenges in an automated browser by pairing computer-vision models with a multimodal language model, without third-party anti-captcha services or Tampermonkey scripts.
Bright Data MCP
brightdata.comAn MCP server that gives AI agents real-time access to public web data: search results, page scraping to Markdown or HTML, structured extraction from major platforms, and remote browser automation, with bot detection, CAPTCHAs and proxy rotation handled automatically.
Spider
spider.cloudA concurrency-first web crawling and scraping engine for Rust that streams pages as they are fetched and renders JavaScript only on pages that need it. It scales from a single script to a distributed fleet, and the same engine also runs a hosted cloud service.
Open Interface
github.comA desktop application that lets an LLM such as GPT-4o control the computer directly, planning and executing keyboard and mouse actions from a plain-language request.