The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
- agent
- vlm
- vision
- computer-use
Repository Index
47,133 repositories indexed
1–23 of 23 · Most stars
Playwright MCP server
JavaScript in-page GUI agent. Control web interfaces with natural language.
The SDK to extract data and interact with any site on the web. Get started with Claude Code, Codex, Eve, Mastra, and more.
See interfaces like a human. E2E testing in natural language.
- testing
- browser-use
- computer-use
- gpt-operator
Open-source Grok Bot alternative with a virtual machine that bots can use
🌐 The open-source Agentic browser; alternative to ChatGPT Atlas, Perplexity Comet, Dia.
- browser
- browseros
- chromium
- linux
Open-source AI agent for web automation. Use your real, logged-in browser to automate daily tasks.
Next generation e2e testing framework for web and mobile apps.
Chrome MCP Server is a Chrome extension-based Model Context Protocol (MCP) server that exposes your Chrome browser functionality to AI assistants like Claude, enabling complex browser automation, content analysis, and semantic search.
Let AI agents use your real, logged-in browser without interrupting your work. CLI + extension for browser automation across any shell-capable AI agent.
A Claude Skill to give your agent the ability to use a web browser
The AI toolkit for building reliable browser automations
- automation
- browser
- claude-code
- codex
Open-source self-improving QA agent for software teams. A test harness with memory. Write tests in natural language for web and mobile. agent-qa learns from every run, adapts to UI changes, and catches regressions before you ship.
- playwright
- end-to-end-testing
- ai-testing
- ai-agents
AI coworkers that run your work. Self-hostable, AGPL-3.0.
Scout: the open-source browser agent, by Outcrawl. Mirrored automatically from Outcrawl's own repository.
Bops: a team of AI bots that run your business ops, each with its own computer, email and phone number. bops.bot
- ai-agents
- business-automation
- computer-use
- electron
Xiryn — the open-source personal agent. Does everything Muse, Grok Bot and Dots do, on your own computer: each agent gets its own Linux desktop in Docker, any model with your keys, an encrypted vault, and control from Telegram.
Agentic browser control driven by your own Claude / Cursor subscriptions
- ai-agent
- browser-automation
- cdp
- chrome-extension
Translatedsilkpulse is an AI-native remote device debugger: it lets AI agents directly view, diagnose, and operate web pages running on remote devices—live H5 pages, mobile browsers, webviews, and every place local DevTools cannot reach.
The World's First Out-of-the-Box Computer Use Agent Powered by Gemini-CLI @openmule
- agent
- ai
- computer-use
- gacua
The AI-native browser automation library. Snapshot + ref targeting — born from OpenClaw, built for agents, by agents.
A vision-first browser agent with self-healing deterministic replay.