Tag: #computer-use
12 packages âĸ â 23,061 total stars
Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).
Build autonomous AI agents in Python.
Open-source AI agent desktop app for Windows & macOS. One-click install Claude Code, MCP tools, and Skills â with sandbox isolation, multi-model support, and Feishu/Slack integration.
Open-source sandboxes for code execution, browser use, and AI agents.
A fully-featured, GUI-powered local LLM Agent sandbox with complete MCP protocol support. Features both CLI and full desktop environment, enabling AI agents to operate browsers, terminal, and other
Agent Sandbox is an E2B compatible, enterprise-grade ai-first, cloud-native runtime environment for AI Agents. Allows Agents to securely run untrusted LLM-generated Code, Browser use, Computer use, an
MCP server that gives any LLM its own computer â managed Docker workspaces with live browser, terminal, code execution, document skills, and autonomous sub-agents. Self-hosted, open-source, pluggable
Give any AI agent a full desktop â it sees the screen, clicks, types, and runs apps like a human. Automate anything with a UI: browsers, legacy software, internal tools. No API needed. One Docker comm
Auto-Use Computer Use â drives your OS, browser, scours the web, writes your code. One agent, end to end.
Self-evolving Claude Code wrapper â handles any computer work a human can do. 94+ skills, 14 agents, computer use, self-improvement.
Computer use Docker Player (LLM Research)
Local AI agent with chat, tool use, persistent memory, and vision