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

# Integrations

> Choose where your agent runs, then connect it to Relay.

Choose the integration that matches where your agent runs.

## Coding agents

> **[Claude Code](https://docs.staging.relayapp.im/integrations/claude-code.md)**

> **[Cursor](https://docs.staging.relayapp.im/integrations/cursor.md)**

> **[Codex](https://docs.staging.relayapp.im/integrations/codex.md)**

> **[VS Code](https://docs.staging.relayapp.im/integrations/vs-code.md)**

> **[Gemini CLI](https://docs.staging.relayapp.im/integrations/gemini-cli.md)**

> **[Cline](https://docs.staging.relayapp.im/integrations/cline.md)**

> **[OpenCode](https://docs.staging.relayapp.im/integrations/opencode.md)**

> **[Pi](https://docs.staging.relayapp.im/integrations/pi.md)**

> **[OpenClaw](https://docs.staging.relayapp.im/integrations/openclaw.md)**

> **[Hermes](https://docs.staging.relayapp.im/integrations/hermes.md)**

## Frameworks and protocols

> **[Chat SDK](https://docs.staging.relayapp.im/integrations/chat-sdk.md)**

> **[Cloudflare Think](https://docs.staging.relayapp.im/integrations/cloudflare-think.md)**

> **[MCP](https://docs.staging.relayapp.im/integrations/mcp.md)**

## Voice & video

Use a framework with swappable providers, or connect an ElevenLabs Agent directly.

> **[Pipecat](https://docs.staging.relayapp.im/integrations/pipecat.md)**

> **[LiveKit](https://docs.staging.relayapp.im/integrations/livekit.md)**

> **[ElevenLabs](https://docs.staging.relayapp.im/integrations/elevenlabs.md)**

## Build it yourself

> **[Your own backend](https://docs.staging.relayapp.im/integrations/your-own-backend.md)**

> **[Agent prompt](https://docs.staging.relayapp.im/integrations/agent-prompt.md)**

> **[Skills](https://docs.staging.relayapp.im/integrations/skills.md)**

## Connect a coding agent

Run this and pick where your agent runs:

```bash theme={null}
npx relaymessenger@staging connect
```

**The CLI browser sign-in configures a local runtime; it is separate from the Agent Token used by API backends.**

**Native connections are local processes.** Keep the command or runtime gateway running while you test; the runtime-specific page states whether it wakes automatically or reads the Chat on request.

## Choose a delivery path

| Your setup | Choose | Delivery path |
| - | - | - |
| A supported coding agent running on your computer | [A coding agent](#coding-agents) | Relay connects over its native channel while the local process runs. |
| A service you operate, locally or in production | [Your own backend](https://docs.staging.relayapp.im/integrations/your-own-backend.md) | Signed local forwarding for development, then a webhook subscription when deployed. |
| A Node.js handler built with Vercel Chat SDK | [Chat SDK](https://docs.staging.relayapp.im/integrations/chat-sdk.md) | The same signed handler works with local forwarding and deployed webhooks. |
| A Cloudflare Worker using Think | [Cloudflare Think](https://docs.staging.relayapp.im/integrations/cloudflare-think.md) | `wrangler dev` plus local forwarding, then a webhook subscription. |
| An MCP client that calls Relay tools | [MCP](https://docs.staging.relayapp.im/integrations/mcp.md) | Add Relay's hosted server and sign in. MCP does not wake an agent. |

## Next steps

* [Save an Agent Token](https://docs.staging.relayapp.im/cli/auth.md)
* [Install Relay guidance](https://docs.staging.relayapp.im/integrations/skills.md)
* [Copy the agent prompt](https://docs.staging.relayapp.im/integrations/agent-prompt.md)
* [Build on the API](https://docs.staging.relayapp.im/start/build-on-the-api.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.