Open-Source Computer-Use and Browser Agents

BrowserOS neo is a secondary Chromium browser for AI agents handling web tasks that require signed-in accounts. Agents work in their own tabs while you continue browsing, with a live view of their actions.

agent-desktop lets developers give AI agents control of macOS apps such as Finder, Safari and Xcode. It identifies controls through the app's accessibility tree, so agents can act on buttons and text fields by their UI structure.

Obscura is a headless browser engine for developers building AI agents and web scraping systems with many independent sessions. Each session starts with fresh state, keeping cookies, logins and cached data separate between tasks.

agent-browser lets AI agents interact with websites through compact text snapshots and references to specific page elements. It's for developers connecting coding assistants or other agents to a browser without sending them the full page HTML.

OpenWork is a desktop workspace for knowledge workers who want AI agents to work on their files and connected services. Built on OpenCode, it's a point-and-click alternative to Claude Cowork and Codex.

Cua supplies desktops and automation tools for developers building AI agents that operate native apps and browsers. You bring your own agent and model; Cua provides the computer environment and ways to interact with it.

VoxInput is an open-source dictation tool for Linux and macOS that types spoken words into the active application. It's for people who want speech input across their desktop, including applications without their own dictation feature. On Linux, it also works in the system console.

Kerlig is a paid AI writing assistant for Mac that helps with emails, Slack replies and Jira tickets in the apps you already use. It combines text editing with document chat and an agent that can read your screen and use your apps.

Open Cowork is a desktop AI agent for Windows and Apple Silicon macOS that uses cloud model APIs to carry out tasks on your computer. It's a Claude Cowork alternative for people who want a graphical interface for document work and app automation. The app is free and open source under MIT, but the agent needs an API key and internet access; model requests go to your chosen provider.

Frona is a self-hosted AI assistant for people who want agents to carry out tasks through chat with controlled access to files, networks and accounts. Agents can work independently or delegate parts of a task to other agents.

Guaardvark is a local AI studio for people who want document chat, task automation and media production on their own hardware. It brings those jobs into one interface and coordinates their use of the GPU.

OwnPilot is a self-hosted AI assistant for people who want personal records and agents that can carry out tasks in one web interface. It supports local model backends as well as cloud providers.

Libre WebUI is a self-hosted AI workspace for individuals and teams who want chat, document research and AI agent tasks on infrastructure they control. You can use local models or connect a remote provider of your choice.

ZeroClaw is a personal AI agent for people who want an assistant running on their own computer or server. It can use a shell and browser, respond through messaging apps and perform scheduled tasks.

LM Studio runs downloaded language models for conversations and tasks on your computer. Its Bionic agent helps people create documents, write software and carry out work using local or frontier open models.

Agent S is a computer-use AI agent framework for developers and researchers building desktop automation. It takes natural-language tasks and operates desktop and web applications through their screen interfaces, without requiring an API integration for each app.

Stagehand is an open-source browser agent SDK for developers automating websites and collecting structured data in local Chrome. Model inference is separate from browser execution: direct provider calls send model context remotely, while a custom callback can connect a self-hosted model. Local runs require Chrome.

Agent Zero is a self-hosted AI agent framework for people who want an assistant to carry out research, coding, and document work on a computer. You can watch its actions and intervene in the same desktop with your mouse and keyboard.

Row-Bot is a local AI assistant for people who want to research, create documents and automate work on their own computer. It combines conversations with memory and agents that can continue working on longer tasks.

Codex iOS Assistant connects Codex on your Mac to your iPhone so the assistant can perform phone actions and retrieve phone context. It's for people who want to bring information from their phone into their work with Codex.

Agent QA is a source-available AI testing agent for developers and software teams testing web, Android and iOS apps. You describe a user journey and its expected results in plain English. It tests the real interface and carries observations from earlier runs into later ones, so it can account for how your app behaves.

h5i gives AI agents tools to investigate vulnerabilities in web applications you own or are authorized to test. Teams can review the evidence behind findings and turn confirmed attack flows into security regression checks.

WebVoyager is a Python AI agent that controls a browser on your machine or a Linux server to carry out tasks on live websites. It's a research project for developers studying browser automation. Model decisions depend on OpenAI's cloud API, which receives page observations and requires an API key and internet access; the local browser doesn't provide local model inference.

BAH Browser is an MIT-licensed desktop browser for people who want an AI agent to carry out web tasks in their own browser session. It runs on Windows and combines a tabbed Chromium browser with an assistant that reads pages, clicks links and fills forms in response to plain-language requests.

cc-haha is a desktop workspace for Claude Code and AI agents. It helps developers delegate coding tasks in local projects while keeping edits and approvals visible.

ResumeForge is a Chinese-first workspace for job seekers who want to keep resumes, vacancies and interview preparation together on their own computer. It separates confirmed experience from AI-written wording to help catch invented claims.

Lemon AI is a local AI agent for people who want to research topics, write code and analyze data on their own hardware. It also lets you revise generated HTML reports and pages without asking the agent to recreate the whole result.

Browser MCP connects AI applications to your everyday browser so they can automate tasks in services you're already signed into. It's for people who want browser automation through their AI assistant without opening a separate browser session.

UFO³ is a self-hosted AI agent framework for developers and researchers automating tasks across Windows, Linux and Android devices. Its Galaxy coordinator splits a request into connected tasks, assigns them to suitable devices and tracks work that depends on results from another machine. The Python project is open source under the MIT license.

Soul-of-Waifu is an AI companion app for creating characters and roleplaying with them. A character carries the same personality and memories between conversations, RPG campaigns and a desktop companion.

Browser4 is a browser automation engine for developers building AI agents, web research tools, and data collection workflows. It controls real Chrome browsers and handles interactive pages that require clicks, forms, or JavaScript before their data is accessible.

Enconvo is a native Mac AI assistant for people who want help with writing, research and tasks inside their everyday apps. It uses screen and selected-text context so you can ask about what you're working on without moving everything into a separate chat.

WebBrain is an AI browser agent for people who want to ask questions about pages or delegate web tasks from a sidebar. It works in your existing browser, including signed-in tabs, and starts in read-only Ask mode.

OpenAdapt automates repeated work in application interfaces that APIs can't reach. Teams and AI agent builders can turn a demonstrated task into an inspectable program, approve it for use, and check that each run produces the agreed result.