Browser & Computer Use
41 agents tracked · Open-source-first, with limited public GitHub comparators · Ranked by trust score · Updated 2026-08-29 09:32 UTC
HVTracker independently evaluates 41 browser & computer use using daily signals from GitHub, package registries, and security databases. The category is open-source-first, with a limited set of public GitHub-hosted proprietary or source-available comparators when they are important ecosystem reference points. Each agent is scored on activity, adoption, transparency, safety, and identity. The top-ranked browser & computer use is Browser Harness with a trust score of 89.9/100 (Grade A). Other leading projects include Stagehand and OpenClaw.
| # | Agent | Trust | Stars | Language |
|---|---|---|---|---|
| 1 | Browser Harness A Listed Browser Harness | Self-healing harness that enables LLMs to complete any task. | 89.9 | 17.2k | Python |
| 2 | Stagehand A Listed The SDK For Browser Agents | 87.2 | 24.1k | TypeScript |
| 3 | OpenClaw A Listed Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞 | 87.0 | 387.9k | TypeScript |
| 4 | Agent Browser A Listed Browser automation CLI for AI agents | 86.6 | 41.5k | Rust |
| 5 | Skyvern A Listed Automate browser based workflows with AI | 82.5 | 22.9k | Python |
| 6 | Camofox Browser A Listed Stealth headless browser for AI agents — bypass Cloudflare, bot detection, and anti-scraping. Drop-in Puppeteer/Playwrig | 82.2 | 8.9k | JavaScript |
| 7 | Argent B Listed An agentic toolkit to control, debug, and profile iOS and Android apps. Made by Software Mansion. | 78.7 | 2.3k | TypeScript |
| 8 | Browser4 B Listed Browser4 — an AI-native browser engine for autonomous agents, intelligent extraction, and large-scale web automation. | 76.9 | 1.1k | Kotlin |
| 9 | Peekaboo B Listed Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the enti | 74.7 | 5.1k | Swift |
| 10 | Cua B Listed Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data gene | 74.5 | 22.0k | HTML |
| 11 | Browser Use B Listed 🌐 Make websites accessible for AI agents. Automate tasks online with ease. | 73.1 | 111.6k | Python |
| 12 | BrowserOS B Listed 🌐 The open-source Agentic browser; alternative to ChatGPT Atlas, Perplexity Comet, Dia. | 65.7 | 13.4k | TypeScript |
| 13 | OpenCLI B Listed Make Any Website into CLI & Use your logged-in browser by AI agent. | 65.4 | 28.7k | JavaScript |
| 14 | UFO C Listed UFO³: Weaving the Digital Agent Galaxy | 59.9 | 9.6k | Python |
| 15 | Steel Browser C Listed 🔥 Open Source Browser API for AI Agents & Apps. Steel Browser is a batteries-included browser sandbox that lets you auto | 56.6 | 7.6k | TypeScript |
| 16 | UI-TARS Desktop C Listed The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra | 54.7 | 38.7k | TypeScript |
| 17 | BrowserGym agents C Listed 🌎💪 BrowserGym, a Gym environment for web task automation | 54.7 | 1.3k | Python |
| 18 | Magentic-UI C Listed MagenticLite is an experimental agent that works across the browser and local file system | 52.8 | 10.1k | Python |
| 19 | autoMate C Listed Like Manus, Computer Use Agent(CUA) and Omniparser, we are computer-using agents.AI-driven local automation assistant th | 52.7 | 4.0k | Python |
| 20 | Open Computer Use C Listed 👾 Open Computer Use – Open-Source Alternative to Codex Computer Use | 51.8 | 1.8k | Swift |
| 21 | bb-browser C Listed Your browser is the API. CLI + MCP server for AI agents to control Chrome with your login state. | 50.3 | 6.1k | TypeScript |
| 22 | OmniParser D Listed A simple screen parsing tool towards pure vision based GUI agent | 47.4 | 25.3k | Jupyter Notebook |
| 23 | Agent-S D Listed Agent S: an open agentic framework that uses computers like a human | 46.5 | 12.2k | Python |
| 24 | Nanobrowser D Listed Open-Source Chrome extension for AI-powered web automation. Run multi-agent workflows using your own LLM API key. Altern | 46.4 | 13.7k | TypeScript |
| 25 | agent-device D Listed Mobile app automation and verification for AI coding agents. CLI, MCP server, and typed Node.js API for iOS, Android, Ha | 45.8 | 4.3k | TypeScript |
| 26 | Browser Use Web UI D Listed 🖥️ Run AI Agent in your browser. | 45.0 | 16.3k | Python |
| 27 | MolmoWeb D Listed | 42.7 | 589 | Python |
| 28 | UI-TARS D Listed Pioneering Automated GUI Interaction with Native Agents | 40.3 | 11.4k | Python |
| 29 | Understudy D Listed An understudy watches. Then performs. | 39.0 | 456 | TypeScript |
| 30 | Agent-E D Listed Agent driven automation starting with the web. Try it: https://www.emergence.ai/web-automation-api | 37.5 | 1.2k | Python |
| 31 | OpenCUA D Listed [NeurIPS 2025 Spotlight] OpenCUA: Open Foundations for Computer-Use Agents | 36.0 | 829 | Python |
| 32 | OpenAI CUA Sample App D Listed Learn how to use CUA (our Computer Using Agent) via the API on multiple computer environments. | 35.8 | 1.8k | TypeScript |
| 33 | OpenBrowser D Listed Let AI agents browse the web. An autonomous toolkit for browser-based AI agents. | 34.6 | 9.5k | TypeScript |
| 34 | ScaleCUA D Listed [ICLR 2026 Oral] ScaleCUA is the open-sourced computer use agents that can operate on cross-platform environments (Windo | 30.0 | 1.1k | Python |
| 35 | PyWinAssistant D Needs review The first open-source Artificial Narrow Intelligence generalist agentic framework Computer-Using-Agent that fully operat | 29.5 | 1.3k | Python |
| 36 | Obscura D Listed The headless browser for AI agents and web scraping | 26.9 | 22.4k | Rust |
| 37 | Open Operator D Needs review A template for building web agents with Stagehand on Browserbase | 26.8 | 2.0k | TypeScript |
| 38 | arbigent D Listed AI Agent for testing Android, iOS, and Web apps. Get Started in 5 Minutes. Arbigent's intuitive UI and powerful code int | 23.3 | 634 | Kotlin |
| 39 | openocta D Listed 国产开源的桌面级智能体，信创安全，适用于电脑办公、文档处理、IT运维与安全、市场营销等场景。 | 21.6 | 3.0k | TypeScript |
| 40 | openyak D Listed Open-source local-first AI agent for desktop work. No account, no telemetry: use local models with Ollama/Rapid-MLX or b | 20.9 | 701 | Python |
| 41 | TuriX D Listed This is the official website for TuriX Computer-use-Agent | 18.6 | 3.2k | Python |
Grade = trust band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50 — methodology