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.

Setup

Get Sentō running in about 20 minutes.

A step-by-step walkthrough, written for people who have never touched a VPS before. Pick your host, pick your messaging platform, paste your tokens. Done.

Prefer a guided chat? Answer a few questions and we'll generate your install command.

Try the wizard

Step 1 · Prerequisites

Two things to get first

Do these on your regular computer before picking a host. Takes about 5 minutes. You'll paste these tokens later during sento init.

1A · Claude subscription

Subscribe at claude.ai

Sentō uses your existing Claude plan. No API keys, no per-token billing. Any paid plan works — Pro ($20/mo), Max, Team, or Enterprise.

Go to claude.ai and sign up or log in
Profile menu → Upgrade Plan → pick any paid tier
Confirm payment

1B · Claude Code OAuth token

Run two commands locally

This is the credential Sentō uses to authenticate against your Claude subscription. Treat it like a password.

$npm install -g @anthropic-ai/claude-code

$claude setup-token

A browser opens. Log in with the same account as your subscription and approve. The command prints a token starting with sk-ant-oat01- — copy it somewhere secure.

…

Step 5 · First message

Talk to your agent

Once the installer finishes, your bot will show as online. Send any message in a channel it can see.

The agent reacts with 👀 to confirm it received the message
It starts a short onboarding conversation — asks your role, how you want it to talk, what it should help with
After onboarding, the agent writes what it learned to its own CLAUDE.md config
It's ready to help — try things like:

hey, what's the weather in Tokyo?— browses the web via Playwright
write a python script that reads a CSV and plots it— file + code operations
remember that I prefer concise answers— persistent memory via ClawMem
every day at 9am, DM me the top 3 HN headlines— scheduled tasks

Troubleshooting

Common problems

Problem	Fix
Bot shows offline in Discord	Run `sento restart`, wait 30 seconds
"Node 20+ required"	`curl -fsSL https://deb.nodesource.com/setup_20.x \| sudo bash -`Update Node:
Permission errors on install	You're running as root. Create a regular user and re-run.
Playwright crashes	VPS likely has <2 GB RAM. Resize to at least 2 GB.
Message Content Intent error	Re-enable it in Discord Developer Portal → Bot tab.
Agent doesn't respond	Check channel permissions — bot needs View Channel + Send Messages.

Stuck?

We're happy to help

Open an issue on GitHub — real humans read every one.

Open an issue GitHub repo