11 Browser Automation tools (all free)
11 Browser Automation resources, picked out of 3 saved Instagram reels and 15 liked tweets, from creators like @ctatedev, @browser_use, @Shpigford. 11 of them are free, freemium or open source.
agent-browser is an open-source browser automation CLI developed by Vercel Labs designed specifically for LLM agents. It provides fast automation with token-efficient accessibility snapshot diffing, visual regression testing, and persistent Chrome DevTools Protocol connections. It integrates with tool ecosystems like Claude Code and remote browser providers.
Browser Use Cloud provides managed remote browser infrastructure for AI agents to automate web tasks without running local browser instances. It handles stealth navigation, provides live session views and CDP endpoints, and automatically saves learned workflows into reusable skill files to speed up repeat runs.
This repository hosts a collection of fully functional example applications built on the Hyperbrowser platform and SDK. It includes standalone web tools for tasks like automated API endpoint discovery (DeepCrawler) and extracting design systems directly into Markdown (designmd-url). It is useful as a reference library for developers building autonomous web agents, scraping workflows, and browser automation tools.
PinchTab is a lightweight Go binary and orchestrator that lets AI agents and scripts control Chrome through a standard HTTP API. Instead of sending heavy screenshots to multimodal models, it extracts the accessibility tree to cut token usage significantly while offering stealth injection to bypass bot detection. It operates with zero configuration and includes a built-in real-time dashboard for managing multiple browser instances.
agent-browser Environments is a demo and integration showcasing vercel-labs/agent-browser running within isolated compute environments like Vercel Sandboxes. It lets AI agents quickly boot pre-configured snapshots to navigate URLs, take screenshots, and extract web page data on demand.
autobrowse is an AI agent skill from Browserbase that creates reliable web automation scripts through iterative trial and error. Inspired by autoresearch harness concepts, an inner agent runs the task while an outer agent diagnoses execution failures and refines instructions until the workflow passes consistently. It saves working solutions into reusable skill definitions for tools like Claude Code.
Autotab is an AI digital worker that operates browser software using mouse and keyboard actions rather than custom API integrations. You teach it by demonstrating a workflow once, which creates an editable step-by-step action scaffold that can run locally or in the cloud on demand or on a schedule. It combines demonstration learning with human-in-the-loop steering to execute multi-step repetitive tasks reliably.
browse.sh is an open directory of website-specific automation recipes (SKILL.md) paired with a dedicated CLI by Browserbase. It provides AI agents with pre-mapped DOM selectors, API routes, and execution steps, reducing token consumption and navigation errors. Agents can execute tasks locally via Chromium or offload sessions to remote cloud browsers.
An open-source setup script and service stack that turns any Ubuntu server into a 24/7 Claude Code automation assistant. It connects Claude Code to a persistent Chromium browser session via Browser Use Cloud and gives you an optional Telegram bot to trigger tasks on the go. When the agent hits CAPTCHAs or login walls, it provides a live browser view URL so you can complete manual authentication.
A Python and Selenium automation tool designed to create Google accounts in bulk from a command-line interface. It attempts to bypass phone verification through UI skip buttons or via 5sim API integration for automated SMS retrieval, while utilizing proxy rotation and human-like typing delays to avoid bot detection.
Playwright CLI provides a command-line interface for automating browsers using Playwright. Unlike traditional full-tree model integrations, it exposes actions as concise commands that keep context usage token-efficient for agents like Claude Code and GitHub Copilot. It includes support for persistent sessions, DOM element snapshots, live monitoring dashboards, and media recording.