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.

macOS install

Sentō runs on macOS, with one caveat: macOS doesn't have systemd or a persistent cron user session in the way Linux does, so the agent only runs while your Mac is on and you've launched it. For anything that needs 24/7 uptime, use a VPS or Docker instead.

macOS is the only host that supports the iMessage channel, since iMessage requires local access to the Messages database.

Prerequisites

macOS 13 (Ventura) or later
Node 20+ (brew install node or nodejs.org)
A Claude subscription (Pro or Max) — authentication happens during setup

Install

npx sentoagent init

Same flow as the VPS install. The installer detects macOS and skips the Linux-specific cron persistence steps.

iMessage-specific setup

If you pick iMessage as the channel, you also need to grant Full Disk Access to your terminal:

System Settings → Privacy & Security → Full Disk Access
Click +, navigate to Applications → Utilities → Terminal (or iTerm, Warp, Ghostty — whichever you use)
Toggle it ON
Restart your terminal

Without this, Sentō can't read ~/Library/Messages/chat.db and the iMessage agent can't receive messages.

After install

The agent runs in a tmux session. To check on it:

tmux attach -t <agent-name>

Ctrl-b d to detach, sento status to check from outside the session.

Restarting after reboot

macOS doesn't auto-restart the agent. After a reboot, run:

sento start

Or script it yourself in ~/Library/LaunchAgents/ with a launchd plist if you want full autostart — not included by default.

Development use

macOS is the easiest environment for developing Sentō itself (contributing, testing plugin patches, etc.). Clone the repo and run node bin/sento.js init from your dev checkout instead of npx.