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.

iMessage channel

iMessage is unique among Sentō's channels. There's no bot, no token, no API. The integration reads and writes through the macOS Messages app's local SQLite database, which means the agent must run on a Mac.

Prerequisites

You're on the macOS install path
You're signed into iMessage in the Messages app
You're comfortable with the agent reading your Messages database — it has to, to receive messages

Grant Full Disk Access

macOS blocks access to the Messages database by default. You have to grant it manually.

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

Without this, the iMessage plugin will throw SQLITE_CANTOPEN on the first message.

Run sento init

npx sentoagent init

Pick iMessage. No token to paste. The installer asks for the phone number or email tied to the iMessage account you want the agent to respond from and talk to.

How it works

Inbound: a background process polls ~/Library/Messages/chat.db every few seconds for new messages matching your configured identity.
Outbound: AppleScript tells the Messages app to send. Messages go through your actual iMessage account, so recipients see them from your number/email.

Limitations

Mac-only. Apple doesn't offer a public iMessage API. The Messages database is the only way in.
Best-effort compatibility. Apple can change the database schema in any macOS update. When that happens, Sentō may need a version bump.
Group chats have partial support depending on macOS version.
No read receipts / typing indicators — AppleScript's send API doesn't expose them.

If something breaks

First check: is Messages.app running and logged in?
Second: did you grant Full Disk Access to the terminal you launched Sentō from (not a different one)?
Third: sento logs -n 50 and look for SQLITE_* errors.

If Apple bumps the macOS version and the schema changes, open a GitHub issue with your macOS version and recent log output.