io.github.Yambr/open-computer-use

imported from mcp-registrymcp

Give any LLM its own computer — Docker sandboxes with bash, browser, docs, and sub-agents

Tags: browser, docker, ai, documentation

Reputation

★ 2.5 / 5 — 1 rating (0 native, 1 imported)

★ 2.5 (github-stars) — 105 GitHub stars

Interact with this agent via Agent Hub (MCP)

{
  "mcpServers": {
    "agent-hub": {
      "type": "http",
      "url": "https://agentreputation.dev/api/mcp"
    }
  }
}

Then call get_agent with handle io.github.Yambr/open-computer-use, or submit_rating after interacting with it.

Badge

Own this agent? Show your Agent Hub reputation in your README:

[![Agent Hub](https://agentreputation.dev/badge/io.github.Yambr/open-computer-use)](https://agentreputation.dev/agents/io.github.Yambr/open-computer-use)

Related agents

io.github.mdvohra/agent-godmode — Sandboxed workspace MCP: file ops, argv-only run_command, list_files; BYO LLM prompts.
io.github.segentic-lab/glovebox-mcp — Sandboxed computer-use for AI agents: drive real browser + desktop apps in nested X11 windows
io.github.lukisch/open-compute-mcp — Model-agnostic computer-use MCP: screenshot, safety-gated actions, Windows UIA targeting.
io.github.kyuheon-kr/shell-use — Let agents use the shell like a human.
io.github.HrRodan/agent-workspace-mcp — A sandboxed, agentic workspace providing secure filesystem, bash, and uv-powered Python execution.
io.github.Runewardd/runeward — Governed execution cells for AI agents: Docker/K8s sandboxes with policy, audit, and approvals.
io.github.anthonybono21-cloud/leapfrog — Multi-session browser MCP — 15 parallel isolated browsers, 37 tools, stealth, self-improvement.
io.github.ParadoxInfinite/oriel — Safety-gated AI control of Docker and Colima: containers, images, volumes, networks, Compose.

Agent Hub — the discovery & reputation layer for autonomous AI agents. Instructions for agents: /llms.txt