Browser Automation
Browser automation uses software to control web browsers and perform actions such as navigating pages, clicking controls, submitting forms, and checking results. It reduces repetitive manual work and supports automated testing, data collection, and workflows that depend on websites. Automation can run in a visible browser or in the background, and may follow precise scripts or use more flexible, language-driven instructions.
Open source tools in this area include browser drivers, testing frameworks, scraping utilities, and interfaces that let software agents interact with web pages. When choosing one, consider supported browsers and languages, reliability on dynamic sites, accessibility and debugging features, license, maintenance activity, and deployment requirements. Browser automation is useful to developers, QA teams, researchers, and organizations that need repeatable browser tasks or integration with existing applications.
29 repositories · updated October 4, 2026
Memoh: Give AI Agents Dedicated Cloud Computers
Memoh is a multi-agent platform that gives each agent an isolated, always-on workspace with a desktop, browser, network access, and long-term memory. Use your own API keys or host agents such as Claude Code and Codex, either in Memoh Cloud or on your own infrastructure.
browser-rs-mcp: Share Chrome with AI Agents
A Rust MCP server that lets multiple AI agents control separate tabs in one shared Chrome profile. It provides browser automation through Chrome DevTools Protocol without requiring a Node.js runtime.
astron-rpa: Automate Desktop and Web Workflows
AstronRPA is a visual RPA desktop application for building workflows that automate desktop software and web pages. It combines low-code workflow design with agent integration and supports enterprise deployment, scheduling, and API or MCP triggers.
OpenBot: Govern and Run AI Coworkers on Your Infrastructure
OpenBot is a self-hosted platform for running AI coworkers with their own browser, files and tools. It connects agents through AG-UI and routes computer actions through configurable policy and audit controls.
bux: Run a Persistent Browser Automation Agent on Your Server
bux runs Claude Code as an always-on agent with a persistent Chromium browser, Browser Use Cloud, and optional Telegram access. It is for people who want browser tasks available from a VPS or other Ubuntu machine.
MechanicalSoup: Automate Website Interaction in Python
MechanicalSoup is a Python library for scripting website interactions through HTTP sessions and HTML parsing. Use it to follow links, manage cookies, and submit forms when a site does not require JavaScript.
OpenWebAgent: Build Web Agents for Large Language Models
OpenWebAgent is a toolkit for building web agents that automate interactions with webpages using language or multimodal models. It pairs a Chrome extension with a configurable server, aimed at developers integrating their own models.
helium: A Privacy-Focused Chromium Web Browser
Helium is a Chromium-based browser focused on privacy, unbiased ad-blocking, and a simpler browsing experience. It is aimed at people who want Chromium compatibility without extra browser clutter.
pinchtab: Control Chrome for AI Agents
PinchTab is a local-first Go server and CLI that lets AI agents control Chrome through an HTTP API. It supports token-efficient page interaction, persistent profiles, and multiple browser instances.
CloakBrowser: Automate Chromium with Modified Fingerprints
CloakBrowser wraps a custom Chromium build with source-level fingerprint changes and Playwright- and Puppeteer-compatible APIs. It is aimed at browser automation and web scraping where standard browser automation is frequently flagged by bot detection.
chrome-devtools-mcp: Give Coding Agents Chrome DevTools Access
Chrome DevTools MCP lets coding agents control and inspect a live Chrome browser through MCP or a CLI. Use it for browser automation, debugging, and performance analysis when your workflow needs access to real browser behavior.
shortest: Write End-to-End Tests in Natural Language
Shortest is a TypeScript end-to-end testing framework that turns natural-language instructions into browser tests, using Anthropic Claude and Playwright. It suits teams that want to describe user flows plainly while retaining hooks for custom assertions and setup.