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.

Introduction

Sentō is an open-source framework for running persistent AI agents on your Claude Code subscription. You bring a Claude plan (Pro or Max). Sentō gives you an agent that lives in Discord, Telegram, Slack, or iMessage, stays online 24/7, remembers you across conversations, and can actually do things — browse the web, write code, run scheduled tasks, talk to other agents.

It's built on top of Claude Code using the plugins marketplace. It's MIT licensed. It runs on a VPS, in Docker, or locally on macOS.

What you get

An agent with a name, a personality, and a persistent memory that lives in the messaging platform you already use.
Flat-rate pricing — no per-token API bills. Your Claude subscription is the agent's compute.
A self-healing Guardian process that watches the agent, auto-restarts on crashes, and can page you via your primary channel.
Agent-to-agent messaging — pair multiple agents and let them coordinate with signed HMAC messages over HTTP.
A single CLI (sento) for everything: install, config, logs, restart, update, pair with other agents.

What you don't get

Sentō isn't a hosted service. There's no control plane, no dashboard, no monthly SaaS bill. Your agent runs on infrastructure you own or rent. If you want a fully-hosted solution, this isn't it.

Sentō also isn't an LLM or a model. It's the scaffolding around Claude Code that makes Claude act like a persistent agent instead of a chat window you open and close.

Who it's for

Developers who want a long-running AI assistant they fully control.
Solo founders or small teams who need an agent to handle repeatable work (marketing ops, monitoring, scheduling) without racking up API bills.
Anyone who already pays for a Claude subscription and wants more from it than a browser tab.

What you get

What you don't get

Who it's for

Read next