Does Sentō need a pay-per-token API key?

No. Sentō authenticates using the same Claude Code OAuth token you already sign in with on your machine, and that token is tied to your Claude Pro or Max subscription, not to a pay-as-you-go Anthropic Console key. Every message your agent sends counts against your subscription, not a separate metered invoice. If you prefer to run on a pay-per-token API key instead, Sentō supports that too.

How much does it cost to run a Sentō agent 24/7?

Zero extra on top of the Claude subscription you're already paying for. A Pro plan is enough for a daily-driver agent; Max unlocks heavier 24/7 workloads. Sentō also routes everything through Claude Code, which means you get Claude Code's own context and caching optimizations, so the same token goes further than it would through a raw API call. You never see a separate token bill.

How long does setup take?

About five minutes. Run `npx sentoagent init`, answer a few questions about model, channel, and bot token, and the agent launches and comes online on Discord, Telegram, Slack, or iMessage.

What makes Sentō self-healing?

Every agent runs under a Guardian + Watchdog pair. Guardian restarts the agent process if it crashes; Watchdog watches Guardian. If the agent goes down, it's back up before you notice, and you can fix anything right from Discord without SSH'ing in.

Can two Sentō agents talk to each other?

Yes. Sentō is the first framework with built-in, secure agent-to-agent messaging. Every message is HMAC-SHA256 signed, pairing requires mutual consent on both sides, and rate limiting is on by default.

Which messaging platforms are supported?

Discord, Telegram, Slack, and iMessage out of the box. You can run on a VPS, inside Docker, or directly on macOS.

Is Sentō open source?

Yes, MIT licensed. The source lives at github.com/sentoagent/sento and the package at npmjs.com/package/sentoagent.

Docker install

Sentō ships with a Dockerfile that gives you full VPS parity in a container: non-root sento user, @reboot cron for persistence within the container, Guardian running alongside Claude Code.

Prerequisites

Docker 24+
A Claude Code OAuth token — since Docker runs non-interactively, the browser auth flow can't work. Generate a token on your local machine first: npm install -g @anthropic-ai/claude-code && claude setup-token. It starts with sk-ant-oat01-….
A bot token for your chosen channel

Build the image

git clone https://github.com/sentoagent/sento
cd sento
docker build -t sento .

The image runs as a non-root sento user (Claude Code refuses --dangerously-skip-permissions as root) and keeps npm globals under ~/.npm-global.

Run with env vars

docker run -d \
  --name sento-agent \
  -e CLAUDE_CODE_OAUTH_TOKEN="sk-ant-oat01-..." \
  -e DISCORD_BOT_TOKEN="your-bot-token" \
  -e AGENT_NAME="kai" \
  -e CHANNEL="discord" \
  -v sento-data:/home/sento/workspace \
  sento

Volume mount the workspace so CLAUDE.md, memory, and credentials survive container restarts.

Docker Compose (multi-agent)

For more than one agent, use Compose:

version: "3.9"
services:
  kai:
    image: sento
    environment:
      - CLAUDE_CODE_OAUTH_TOKEN=${CLAUDE_TOKEN}
      - DISCORD_BOT_TOKEN=${KAI_DISCORD_TOKEN}
      - AGENT_NAME=kai
      - CHANNEL=discord
    volumes:
      - kai-data:/home/sento/workspace
  mira:
    image: sento
    environment:
      - CLAUDE_CODE_OAUTH_TOKEN=${CLAUDE_TOKEN}
      - TELEGRAM_BOT_TOKEN=${MIRA_TG_TOKEN}
      - AGENT_NAME=mira
      - CHANNEL=telegram
    volumes:
      - mira-data:/home/sento/workspace

volumes:
  kai-data:
  mira-data:

Checking health

docker exec -it sento-agent sento status
docker exec -it sento-agent sento logs -n 40

Or shell in and treat it like a VPS:

docker exec -it sento-agent bash

Why Docker parity matters

Every feature that works on a VPS works in Docker: Guardian, cron @reboot, tmux, the full CLI, agent-to-agent pairing. There's no "lite mode." The container runs the same way a Linux user does.