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

# Integration guide overview

> Connect Claude Code, Codex, Gemini CLI, OpenClaw, Pi, and other clients to the OmniMux gateway.

Point your **coding CLIs, agents, and desktop clients** at OmniMux with a Base URL and API key so they use models enabled for your account.

## Common settings

| Item                                 | Value                                                |
| ------------------------------------ | ---------------------------------------------------- |
| Console                              | [omnimux.ai/dashboard](https://omnimux.ai/dashboard) |
| API Base URL                         | `https://api.omnimux.ai`                             |
| OpenAI-compatible (most SDKs / CLIs) | `https://api.omnimux.ai/v1`                          |
| Claude / Anthropic-compatible root   | `https://api.omnimux.ai`                             |
| Gemini-compatible                    | `https://api.omnimux.ai/v1beta`                      |
| API key                              | Console token `sk-...`                               |

See [Authentication](/en/guides/authentication) and [Models](/en/guides/models).

## Coding CLIs

<CardGroup cols={2}>
  <Card title="Claude Code CLI" icon="terminal" href="/en/integration-guide/claude-code-cli">
    Anthropic official CLI via Anthropic-compatible gateway.
  </Card>

  <Card title="Codex CLI" icon="code" href="/en/integration-guide/codex-cli">
    OpenAI official CLI with an OpenAI-compatible provider.
  </Card>

  <Card title="Gemini CLI" icon="sparkles" href="/en/integration-guide/gemini-cli">
    Google Gemini command-line tool.
  </Card>

  <Card title="OpenCode" icon="laptop-code" href="/en/integration-guide/opencode">
    Open-source coding agent with a custom provider.
  </Card>

  <Card title="Pi Coding Agent" icon="robot" href="/en/integration-guide/pi">
    Anthropic Messages-compatible setup.
  </Card>

  <Card title="Hermes Agent" icon="comments" href="/en/integration-guide/hermes">
    OpenAI-compatible custom endpoint.
  </Card>
</CardGroup>

## Desktop and IDE

<CardGroup cols={2}>
  <Card title="Claude Desktop" icon="desktop" href="/en/integration-guide/claude-desktop">
    Desktop gateway configuration.
  </Card>

  <Card title="CodeBuddy / WorkBuddy" icon="puzzle-piece" href="/en/integration-guide/codebuddy-workbuddy">
    IDE / plugin-style clients.
  </Card>
</CardGroup>

## OpenClaw (chat channel gateway)

<CardGroup cols={2}>
  <Card title="Manual install" icon="gears" href="/en/integration-guide/openclaw">
    Install OpenClaw Gateway and configure OmniMux multi-protocol providers.
  </Card>

  <Card title="Auto install" icon="wand-magic-sparkles" href="/en/integration-guide/openclaw-auto">
    Deploy with OpenClaw Manager.
  </Card>

  <Card title="OpenClaw + Feishu" icon="message" href="/en/integration-guide/openclaw-feishu">
    Feishu / Lark bot setup.
  </Card>

  <Card title="OpenClaw + Telegram" icon="paper-plane" href="/en/integration-guide/openclaw-telegram">
    Telegram bot setup.
  </Card>
</CardGroup>

## Checklist

1. Create a token in the console and confirm model scope
2. Use `api.omnimux.ai` as the API host — not the console host
3. Confirm real `model` IDs via `GET /v1/models` or the console
4. Smoke-test with a short chat before wiring agents or channels

Full HTTP surface: [API manual](/en/api-reference/overview).