> ## Documentation Index
> Fetch the complete documentation index at: https://docs.yambr.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Self-host quickstart

> Clone the repo, copy .env.example, run two docker compose commands, open localhost:3000.

## 0. Prerequisites

Docker 24.0+ with Compose v2. See [Requirements](/install/requirements) for hardware.

## 1. Clone and configure

```bash theme={null}
git clone https://github.com/Yambr/open-computer-use.git
cd open-computer-use
cp .env.example .env
```

Open `.env` and set at minimum:

```bash theme={null}
# Admin account created on first Open WebUI startup
ADMIN_EMAIL=you@example.com
ADMIN_PASSWORD=change-me

# Open WebUI session signing key — generate a fresh one
WEBUI_SECRET_KEY=...  # openssl rand -hex 32

# Browser-reachable URL of the Computer Use Server
PUBLIC_BASE_URL=http://localhost:8081

# LLM provider (any OpenAI-compatible)
OPENAI_API_KEY=sk-...
# OPENAI_API_BASE_URL=https://openrouter.ai/api/v1  # optional

# PostgreSQL password
POSTGRES_PASSWORD=change-me
```

Full reference: [Configuration](/install/configuration).

## 2. Start the Computer Use Server

```bash theme={null}
docker compose up --build
```

The first build downloads tooling and assembles the workspace image (\~15 min on a decent connection). Subsequent starts take seconds.

When you see `Uvicorn running on http://0.0.0.0:8081`, the orchestrator is live.

Smoke test in another terminal:

```bash theme={null}
curl http://localhost:8081/mcp-info
```

## 3. Start Open WebUI

In a second terminal:

```bash theme={null}
docker compose -f docker-compose.webui.yml up --build
```

The init script auto-installs the Computer Use tool + filter, creates your admin user, and sets `function_calling: native` + `stream_response: true` as the default model params.

Open [http://localhost:3000](http://localhost:3000) and sign in with `ADMIN_EMAIL` / `ADMIN_PASSWORD`.

## 4. Add a model

1. Go to **Admin → Settings → Connections** and add your LLM provider (the same `OPENAI_API_KEY` you set in `.env`, or a separate dedicated key).
2. Go to **Workspace → Models** and enable at least one model.
3. Verify **Function Calling = Native** and **Stream Chat Response = On** — set globally in **Admin → Settings → Models → Advanced Params** if you want these to be the default for every model.

<Tip>
  If tool calls silently don't fire, 99% of the time it's because Function Calling is set to `Default` instead of `Native`. See [Model settings](/install/model-settings).
</Tip>

## 5. Chat

Start a new chat and ask for something tool-worthy:

> *"Create a professional cover letter for a Senior Software Engineer applying to a startup in .docx, three paragraphs."*

You should see:

* The model picks the `docx` skill.
* `bash_tool` and `create_file` calls execute inside a fresh sandbox container.
* A file link appears. A preview iframe auto-inserts below it.

If any of that fails, check [Known bugs](/reference/known-bugs) and [Open WebUI integration traps](/integrations/open-webui).

## Two compose files, on purpose

| File                       | What it runs                                     | Talks to                                                  |
| -------------------------- | ------------------------------------------------ | --------------------------------------------------------- |
| `docker-compose.yml`       | Computer Use Server (`computer-use-server:8081`) | Docker socket, per-chat sandboxes                         |
| `docker-compose.webui.yml` | Open WebUI                                       | `computer-use-server:8081` over the shared Docker network |

They're split so the MCP server and the UI can run on different hosts in production — the split matches how real deployments look. Both files attach to the same external network (`computer-use-net`) that the server creates on first `up`.

## Next

<CardGroup cols={2}>
  <Card title="Configuration" icon="gear" href="/install/configuration">
    Full env var reference.
  </Card>

  <Card title="Docker details" icon="docker" href="/install/docker">
    Why the server needs the Docker socket, resource limits, image layout.
  </Card>

  <Card title="Model settings" icon="sliders" href="/install/model-settings">
    Why Function Calling = Native and streaming matter.
  </Card>

  <Card title="Open WebUI traps" icon="triangle-exclamation" href="/integrations/open-webui">
    Four things that silently break Computer Use in custom deployments.
  </Card>
</CardGroup>