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

# OpenClaw

> Configure Venice as the model provider in OpenClaw for private, uncensored AI across WhatsApp, Telegram, Discord, and other messaging surfaces.

[OpenClaw](https://openclaw.ai) is an open-source, self-hosted AI gateway that connects messaging platforms (WhatsApp, Telegram, Discord, iMessage, Slack) to AI models. Venice AI is available as a built-in provider, giving you access to private and uncensored models from any connected channel.

<Card title="Official Venice Provider Guide" icon="arrow-up-right-from-square" href="https://docs.openclaw.ai/providers/venice">
  Full setup instructions, model list, and configuration options on the OpenClaw docs.
</Card>

## Setup

### 1. Install OpenClaw

<Tabs>
  <Tab title="macOS / Linux">
    ```bash theme={"system"}
    curl -fsSL https://openclaw.ai/install.sh | bash
    ```
  </Tab>

  <Tab title="Windows">
    ```powershell theme={"system"}
    iwr -useb https://openclaw.ai/install.ps1 | iex
    ```
  </Tab>

  <Tab title="npm">
    ```bash theme={"system"}
    npm install -g openclaw@latest
    ```
  </Tab>
</Tabs>

### 2. Run the onboarding wizard

```bash theme={"system"}
openclaw onboard
```

The wizard will walk you through setup. When prompted, select **Venice AI** as your provider from the list, then paste your API key. Get one from [venice.ai/settings/api](https://venice.ai/settings/api) if you don't have one yet.

### 3. Pick a model

During onboarding, OpenClaw shows all available Venice models. Some recommendations:

| Use case   | Model                       | Privacy    |
| ---------- | --------------------------- | ---------- |
| General    | `venice/zai-org-glm-5`      | Private    |
| Reasoning  | `venice/kimi-k2-5`          | Private    |
| Coding     | `venice/claude-opus-4-6`    | Anonymized |
| Vision     | `venice/qwen3-vl-235b-a22b` | Private    |
| Uncensored | `venice/venice-uncensored`  | Private    |

Change your default model anytime:

```bash theme={"system"}
openclaw models set venice/zai-org-glm-5
```

List all available models:

```bash theme={"system"}
openclaw models list | grep venice
```

### 4. Start chatting

Open the terminal UI:

```bash theme={"system"}
openclaw tui
```

Or the web dashboard:

```bash theme={"system"}
openclaw dashboard
```

Or connect a messaging channel (WhatsApp, Telegram, Discord, etc.):

```bash theme={"system"}
openclaw channels login
openclaw gateway
```

## Privacy modes

Venice models in OpenClaw follow the same [privacy tiers](/overview/privacy) as the Venice API:

* **Private** models (GLM, Qwen, DeepSeek, Llama, Venice Uncensored) run on Venice's GPU fleet. Prompts are never stored or logged.
* **Anonymized** models (Claude, GPT, Gemini, Grok) are proxied through Venice with all identifying information stripped. The third-party provider sees Venice as the customer, not you.

## Image and video generation

Install the Venice AI Media skill for image and video generation:

```bash theme={"system"}
openclaw skills install nhannah/venice-ai-media
```

## Resources

<CardGroup cols={2}>
  <Card title="OpenClaw Docs" icon="book" href="https://docs.openclaw.ai/">
    Official documentation
  </Card>

  <Card title="Venice Provider Guide" icon="puzzle-piece" href="https://docs.openclaw.ai/providers/venice">
    Full Venice setup reference
  </Card>
</CardGroup>