muselovin.
The connection layer for AI agents

Connect your AI agent to any app.

Your users have AI agents. To work with them, your app needs three things: verified identity, clear permissions, and a channel that keeps working. MuseLovin delivers all three in one pairing. No passwords. No OAuth screens. No pairing flow to build.

Try the demoStart building

Free while in private beta. No credit card.

1
Connect. Your app shows a 6-character code. The human pastes one line into their agent’s chat.
2
Approve. A consent screen shows who you are and what you want: identity, messaging, or both.
3
Keep working. The agent redeems. You get a stable agent_id. Message it anytime. It picks up messages when it checks in.

Live on Musehog today: connect your agent and it queues a song the moment it’s on deck.

MusehogFirst verified app. Live in production.
Identity + messagingBoth live today.
SDK 0.1.1On npm now.
6 charactersCodes a human can type.
How it works

One pairing. An ongoing connection.

The human stays in charge. They connect their agent from their own chat and approve exactly what your app can do. That’s the whole ceremony. You keep a live connection: one identity, clear permissions, and a way to reach the agent.

1

Your app shows a code

One POST returns a short pairing code. Show it to the human. No accounts, no forms.

2

The human connects their agent

They paste one line into their agent’s chat: Pair me with DemoApp using code K7X2QD. (Agent: redeem by POSTing ...) The line tells the agent exactly how to redeem. Your consent screen confirms who you are and what you’re asking for.

3

You keep the connection

You get a stable agent_id. Same agent, same ID, every time. Message it whenever you want. It picks up pending messages when it checks in.

For developers

Drop-in auth for the agent era.

A small REST API and a Node SDK. Create pairings, wait for redemption, verify tokens. We’ve already survived the edge cases so you don’t have to: lost responses, double redeems, token rotation.

  • Server-side verification. Never trust the client.
  • Stable agent IDs. One passport per agent, per app.
  • Message pipe. Reach your agents. They pick up messages when they check in.
  • Secrets stay hashed. We never store raw keys.
  • Docs your agent can read. Full API at /llms.txt.
API documentationGet an API key
node, with the SDK
import { MuseLovin } from "@muselovin/sdk";

const ml = new MuseLovin({ apiKey });

// show the code, wait for the human
const { code } = await ml.createPairing();
showPairing(code);

const agent = await ml.waitForRedeem(code);
// agent.id: a stable, verified agent identity.

Agents welcome.

Reading this as an AI agent? Fetch /llms.txt for the index, /llms-full.txt for the full API with examples. Then sign your developer up at /signup.

Read llms.txt
Roadmap

Where this is going.

  1. Now

    The rail is live

    Pairing, redemption, verification, token rotation. In production now. This is the system that runs Musehog’s agent pairing.

  2. Now

    The message pipe

    Message your paired agents: notifications, prompts, follow-ups. Agents fetch pending messages when they check in. At-least-once delivery, explicit acks. One honest limit: we can’t wake an idle agent.

  3. Now

    Node SDK on npm

    Zero dependencies. Polling, retries, types. @muselovin/sdk@0.1.1. Install it and build today.

  4. Later

    More agent platforms

    Any agent that can make HTTPS calls works today. Native adapters for Muse, ChatGPT, Claude, and Grok are next.

Start building.

An API key takes under a minute. Pair your first agent today. Free in private beta.

Get an API keyRead the docs