Open Computer Use

Open Computer Use

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.

What is this?

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.

Key differentiators

Works with any MCP-compatible client: Open WebUI, Claude Desktop, LiteLLM, n8n, or your own integration. See docs/COMPARISON.md for a detailed comparison with alternatives.

Live browser streaming

File preview with skills

Claude Code — interactive terminal in the cloud

Sub-agent dashboard — monitor and control

See docs/FEATURES.md for architecture details and docs/SCREENSHOTS.md for 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.

Architecture

Quick Start

git clone https://github.com/Yambr/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

Open http://localhost:3000 — Open WebUI with Computer Use ready to go.

Note: Two separate docker-compose files: docker-compose.yml (Computer Use Server) and docker-compose.webui.yml (Open WebUI). They communicate via localhost:8081. This mirrors real deployments where the server and UI run on different hosts.

Model Settings (important!)

After adding a model in Open WebUI, go to Model Settings and set:

Without Function Calling: Native, the model won't invoke Computer Use tools.

What's Inside the Sandbox

Skills

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.

See docs/SKILLS.md for details.

MCP Integration

The server speaks standard MCP over Streamable HTTP. Connect it to anything:

# Test with curl
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"}}}'

See docs/MCP.md for full integration guide (LiteLLM, Claude Desktop, custom clients).

Configuration

All settings via .env:

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 the Settings Wrapper — see settings-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.

MCP Client Integrations

The Computer Use Server speaks standard MCP over Streamable HTTP — any MCP-compatible client can connect. Open WebUI is the primary tested frontend, but not the only option.

Open WebUI Integration

Open WebUI is 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: Tested with Open WebUI v0.8.11–0.8.12. Set OPENWEBUI_VERSION in .env to pin a specific version.

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 any stock Open WebUI version — just install the tool and filter. Patches are optional quality-of-life fixes applied at Docker build time.

The openwebui/ directory contains:

• tools/ — MCP client tool (thin proxy to Computer Use Server). Required — this is the bridge between Open WebUI and the sandbox.
• functions/ — System prompt injector + file link rewriter + archive button. Required — without it the model doesn't know about skills and file URLs.
• patches/ — Build-time fixes for artifacts, error handling, file preview. Optional but recommended — improves UX significantly.
• init.sh — Auto-installs tool + filter on first startup. Optional — you can install manually via Workspace UI instead.
• Dockerfile — Builds a patched Open WebUI image with auto-init. Optional — use stock Open WebUI + manual setup if you prefer.

How auto-init works

On first docker compose up, the init script automatically:

1. Creates an admin user ([email protected] / admin)
2. Installs the Computer Use tool via POST /api/v1/tools/create
3. Installs the Computer Use filter via POST /api/v1/functions/create
4. Configures tool valves (FILE_SERVER_URL=http://computer-use-server:8081)
5. Enables the filter globally

A marker file (.computer-use-initialized) prevents re-running on subsequent starts.

Note: Open WebUI doesn't support pre-installed tools from the filesystem — they must be loaded via the REST API. The init script automates this so you don't have to do it manually.

Manual setup (if not using docker-compose)

If you run Open WebUI separately, you need to manually:

1. Go to Workspace > Tools → Create new tool → paste contents of openwebui/tools/computer_use_tools.py
2. Set Tool ID to ai_computer_use (required for filter to work)
3. Configure Valves: FILE_SERVER_URL = your Computer Use Server URL
4. Go to Workspace > Functions → Create new function → paste openwebui/functions/computer_link_filter.py
5. Enable the filter globally (toggle in Functions list)
6. In your model settings, set Function Calling = Native

The docker-compose stack handles all of this automatically.

Security Notes

Production tested with 1000+ users on Open WebUI in a self-hosted environment. For public-facing deployments, see the hardening roadmap below.

Current model

• Docker socket: The server needs Docker socket access to manage sandbox containers. This grants significant host access — run in a trusted environment only.
• MCP_API_KEY: Set a strong random key in production. Without it, anyone with network access to port 8081 can execute arbitrary commands in containers.
• Sandbox isolation: Each chat session runs in a separate container with resource limits (2GB RAM, 1 CPU). Containers use standard Docker runtime (runc), not gVisor — they share the host kernel. For stronger isolation, consider switching to gVisor runtime (see roadmap). Containers have network access by default.
• POSTGRES_PASSWORD: Change the default password in .env for production.

Known limitations

• Unauthenticated file/preview endpoints: /files/{chat_id}/, /api/outputs/{chat_id}, /browser/{chat_id}/, /terminal/{chat_id}/ — accessible to anyone who knows the chat ID. Chat IDs are UUIDs (hard to guess but not a real security boundary).
• No per-user auth on server: The MCP server trusts whoever sends a valid MCP_API_KEY. User identity (X-User-Email) is passed by the client but not verified server-side.
• Credentials in HTTP headers: API keys (GitLab, Anthropic, MCP tokens) are passed as HTTP headers from client to server. Safe within Docker network, but use HTTPS if exposing externally.
• Default admin credentials: [email protected] / admin — change immediately in multi-user setups.

Security roadmap

We plan to address these in future releases:

• Per-session signed tokens for file/preview/terminal endpoints (replace chat ID as auth)
• Server-side user verification via Open WebUI JWT validation
• HTTPS support with automatic TLS certificates
• Audit logging for all tool calls and file access
• Network policies for sandbox containers (restrict egress by default)
• Secret management — move credentials from headers to encrypted server-side storage
• gVisor (runsc) runtime — optional container sandboxing for stronger isolation (like Claude.ai)

Ideas? Open a GitHub Issue. Want to contribute? See CONTRIBUTING.md or reach out on Telegram @yambrcom.

Development

# Build workspace image locally
docker build --platform linux/amd64 -t open-computer-use:latest .

# Run tests
./tests/test-docker-image.sh open-computer-use:latest
./tests/test-no-corporate.sh
./tests/test-project-structure.sh

# Build and run full stack
docker compose up --build

Contributing

See CONTRIBUTING.md. PRs welcome!

Community

• Issues & Ideas: GitHub Issues
• Telegram: @yambrcom

License

This project uses a multi-license model:

• Core (computer-use-server/, openwebui/, settings-wrapper/, Docker configs): Business Source License 1.1 — free for production use, modification, and self-hosting. Converts to Apache 2.0 on the Change Date. Offering as a managed/hosted service requires a commercial agreement.
• Our skills (skills/public/describe-image, skills/public/sub-agent): MIT
• Third-party skills: see individual LICENSE.txt files or original sources.

Attribution required: include "Open Computer Use" and a link to this repository.

See NOTICE for details.