Open Computer Use
About
Give any LLM its own computer — Docker sandboxes with bash, browser, docs, and sub-agents
Details
- Author
- yambr
- Categories
- Developer Tools, Automation, Other, AI
Jump to
Setup
Install Open Computer Use in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/yambr/open-computer-use
Follow the installation instructions in the repository README, then restart your MCP client.
MCP server that gives any LLM its own computer — managed Docker workspaces with live browser, terminal, code execution, document skills, and autonomous sub-agents. Self-hosted, open-source, pluggable into any model.
Transformation in progress:the project is being reorganised. The managed dashboard, the hosted MCP endpoint and the hosted docs site are offline and their links have been removed from this repository.chat.yambr.comstays up and may be interrupted while the move is in progress.
If any of this looks useful, a ⭐ on the repo really helps — thanks!
An MCP server that gives any LLM a fully-equipped Ubuntu sandbox with isolated Docker containers. Think of it as your AI's computer — it can do everything a developer can do:
- Execute code— bash, Python, Node.js, Java in isolated containers
- Create documents— Word, Excel, PowerPoint, PDF with professional styling via skills
- Browse the web— Playwright + live CDP browser streaming (you see what AI sees in real-time)
- Run Claude Code— autonomous sub-agent with interactive terminal, MCP servers auto-configured
- Use 13+ skills— battle-tested workflows for document creation, web testing, design, and more
Built for production multi-user deployments.Tested with 1,000+ MAU. Each chat session runs in its own isolated Docker container — the AI can install packages, create files, run servers, and nothing leaks between users. Works seamlessly across MCP clients: start with Open WebUI today, switch to Claude Desktop or n8n tomorrow — same backend, no migration.
Works withany MCP-compatible client: Open WebUI, Claude Desktop, LiteLLM, n8n, or your own integration. Seedocs/COMPARISON.mdfor a detailed comparison with alternatives.
Frontend design — landing page rendered live in the browser tab
Presentations — custom design system, not the default white template
Build your own skills — package recurring work into reusable functions
Claude Code — interactive terminal in the cloud
Sub-agent dashboard — monitor and control
Seedocs/FEATURES.mdfor architecture details anddocs/SCREENSHOTS.mdfor all screenshots.
Pro tip: Create skills with Claude Code in the terminal, then use them with any model in the chat. Skills are model-agnostic — write once, use everywhere.
Multi-CLI sub-agent runtime (v0.9.2.1+): The sub-agent dispatch supports Claude Code (default), OpenAI Codex, and OpenCode (with OpenRouter / qwen / DeepSeek / 75+ providers). FlipSUBAGENT_CLI=claude|codex|opencodein.env— seedocs/multi-cli.mdfor the worked OpenCode + qwen3-coder + OpenRouter recipe.
Looking ahead: a Kubernetes-friendly architecture with object-storage-backed user data and squashfs-packaged skills is being designed indocs/future-architecture/. Docker Compose remains the primary supported path.
OAuth only — no email/password, no SMS. Onchat.yambr.commodels are bundled as a free convenience. The hosted MCP endpoint is offline during the transformation; seedocs/CLOUD.md.
git clone https://github.com/Wide-Moat/open-computer-use.git cd open-computer-use cp .env.example .env # Edit .env — set OPENAI_API_KEY (or any OpenAI-compatible provider) # 1. Start Computer Use Server (builds workspace image on first run, ~15 min) docker compose up --build # 2. Start Open WebUI (in another terminal) docker compose -f docker-compose.webui.yml up --build
Openhttp://localhost:3000— Open WebUI with Computer Use ready to go.
Note:Two separate docker-compose files:docker-compose.yml(Computer Use Server) anddocker-compose.webui.yml(Open WebUI). They communicate vialocalhost:8081. This mirrors real deployments where the server and UI run on different hosts.
After adding a model in Open WebUI, go toModel Settingsand set:
WithoutFunction Calling: Native, the model won't invoke Computer Use tools.
13 built-in public skills + 14 examples:
14 example skills: web-artifacts-builder, copy-editing, social-content, canvas-design, algorithmic-art, theme-factory, mcp-builder, and more.
The server speaks standard MCP over Streamable HTTP. Point any MCP client at your own deployment.
- Self-hosted:http://localhost:8081/mcp. Quick sanity check:
curl -X POST http://localhost:8081/mcp \ -H "Content-Type: application/json" \ -H "X-Chat-Id: test" \ -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}}}'
Custom Skills & Token Management (optional)
By default, all 13 built-in skills are available to everyone. For per-user skill access and custom skills, deploy theSettings Wrapper— seesettings-wrapper/README.md.
Personal Access Tokens (PATs):The settings wrapper can also store encrypted per-user PATs for external services (GitLab, Confluence, Jira, etc.). The server fetches them by user email and injects into the sandbox — so each user's AI has access to their repos/docs without sharing credentials. The server-side code for token injection is implemented (docker_manager.py), but the Open WebUI tool doesn't pass the required headers yet. This is on the roadmap — if you need PAT management,open an issue.
The Computer Use Server speaks standardMCP over Streamable HTTP— any MCP-compatible client can connect. Open WebUI is the primary tested frontend, but not the only option.
Open WebUIis an extensible, self-hosted AI interface. We use it as the primary frontend because it supports tool calling, function filters, and artifacts — everything needed for Computer Use.
Compatibility:This build is strictly built and verified against Open WebUI 0.11.0. The first 3 segments of our build version (v0.11.0.X) always match the Open WebUI base version it targets. If you run a different Open WebUI version, pick the Open Computer Use build whose first 3 version segments match yours — e.g., for Open WebUI 0.8.12 use av0.8.12.Ybuild.
Why not a fork?We intentionally did not fork Open WebUI. Instead, everything is bolted on via the official plugin API (tools + functions) and build-time patches for missing features. This means you can use stockOpen WebUI0.11.0 with this build (the version that the first 3 segments of our build versionv0.11.0.Xmatch) — just install the tool and filter. Patches are applied at Docker build time; strongly recommended — 4 of them affect user-visible UX (artifacts panel, preview iframe, error banners, large tool-result handling). Pullingghcr.io/open-webui/open-webuidirectly skips all of them — seeRequired setup when embedding Open WebUIfor the full checklist.
Running Claude Code through a corporate gateway (LiteLLM, Azure, Bedrock)? See[docs/claude-code-gateway.mdfor the three-path operator recipe.
…
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
