Self-host agentring on your own server

What you'll run

• relay (TypeScript): pairing, messages, call state, push and LiveKit tokens. Runs on your server behind Caddy.
• LiveKit: the call audio, self-hosted in the same compose file.
• daemon (Python): the agentring CLI, the MCP server and the voice AI. Runs next to your agents; behind NAT is fine, it only opens outbound connections.
• Android app (Kotlin): QR pairing, the native call screen and messages.

 your agent ──MCP/CLI──▶ daemon ──WSS (outbound only)──▶ relay ──FCM push──▶ Android app
     ▲                     │                      (your server)                   │
     └── agents.yaml ◀── voice AI (realtime) ◀──────── LiveKit (call audio) ───────┘

What you need

• Somewhere to run the relay: a Linux server with Docker and a domain name, or your own computer with Docker (the phone on the same Wi-Fi, or anywhere over Tailscale).
• A free Firebase project, which is what makes a locked phone ring (guide).
• A key for the voice AI: Gemini (free tier), OpenAI, xAI (Grok) or Phonic.
• An Android phone (8 or newer).

1. Start the relay

Clone the repo and bring up the relay with LiveKit:

git clone https://github.com/mutonby/agentring.git && cd agentring

# On a server with a domain (ports 80, 443, UDP 50000-50100 and TCP 7881 open)
cd deploy && cp .env.example .env && $EDITOR .env
docker compose up -d --build
docker compose logs relay | grep -A2 "API key"

Or, without a server, on your own computer:

# On your own computer, at its LAN or Tailscale IP
cd deploy && cp .env.local.example .env.local && $EDITOR .env.local
docker compose -f docker-compose.local.yml --env-file .env.local up -d --build

On first start, the relay generates an API key (ak_…) and prints it in the log.

2. Install the daemon and pair the phone

On the computer where your agent runs. Install the app from Google Play (or the APK from GitHub Releases) and scan the QR code that agentring pair shows:

uv tool install './daemon[voice]'
agentring init --relay https://relay.example.com --api-key ak_...
agentring pair                                   # scan the QR code with the app
agentring msg "hello"                            # the phone gets a notification
echo GEMINI_API_KEY=... >> ~/.agentring/.env     # or OPENAI_API_KEY / XAI_API_KEY / PHONIC_API_KEY
agentring call "Testing agentring" --ai          # + --provider openai|grok|phonic

3. Connect your agent

With Claude Code it's one line; for the others, see each agent's guide:

claude mcp add agentring -- agentring mcp

Codex · opencode · OpenClaw · Hermes · n8n & scripts

Pick the voice AI

Set AGENTRING_VOICE_PROVIDER in ~/.agentring/.env to use one for every call, from the CLI and from MCP. We compared their latency in this post.

Privacy when you self-host

Everything runs on your own servers and accounts. Messages and call metadata are stored on your relay. Pushes go through your own Firebase project; they are signed, not encrypted, so Google's FCM can read pushed text. Call audio goes through your LiveKit server and, with the voice AI, to the provider you chose; on Google's free tier, Google may use that data to improve its products.

FAQ