Open Computer Use
✨An open-source full-stack framework for autonomous computer agents, enabling control of browsers, terminals, and desktop apps via natural language in Docker VMs. Maintained by coasty-ai under Apache 2.0 license, achieving 82% on OSWorld Benchmark.
Model & Inference FrameworkNatural Language ProcessingMultimodal
Claude Quickstarts
✨A collection of official quickstart projects by Anthropic for the Claude API, featuring complete sample applications for customer support, data analysis, computer control, browser automation, and autonomous coding, deployable via Next.js, Docker, and Python.
wuying-agentbay-sdk
✨A cloud sandbox environment specifically built for AI agents, providing automation capabilities across browsers, desktops, mobile devices, and code spaces with multi-language SDK support.
Agent & ToolingPythonJava
AstronRPA
✨An enterprise-grade Robotic Process Automation (RPA) desktop application that supports low-code/no-code development through a visual designer, enabling rapid workflow construction for automating desktop software and browser pages. Deeply integrated with the Astron Agent platform for seamless collaboration between automation and AI systems.
Agent & ToolingElectronJava
Huginn
✨An open-source automation task agent system that lets you build intelligent agents to monitor online events and perform automated actions, serving as a self-hosted alternative to IFTTT or Zapier.
Agent & ToolingJavaScriptNode.js
browser-use
✨A Python library that makes websites accessible for AI agents, enabling easy automation of online tasks with both local and cloud deployment options.
Agent & ToolingPythonPlaywright
MoLing MCP Server
✨MoLing is a computer-use and browser-use based MCP server that serves as a dependency-free local office AI assistant, enabling file system operations and command execution through system APIs.
Agent & ToolingGoModel Context Protocol
Agent Workflow Memory
✨An AI agent system that induces, integrates, and utilizes workflows through agent memory, achieving 35.6% success rate in web automation tasks.
Agent & ToolingPythonAgent Framework
autotab-starter
✨An automated tab management tool that helps users efficiently organize and manage browser tabs, improving multi-tasking productivity.
SeeAct
✨SeeAct is a system for generalist web agents that autonomously carry out tasks on any given website, focusing on large multimodal models (LMMs) like GPT-4V. It consists of a robust codebase for running web agents on live websites and an innovative framework that utilizes LMMs as generalist web agents.
Agent & ToolingPythonPlaywright