Agent Tincan — AI skill for Claude Code

Agent Tincan

Let your AI agents ask each other for help. Grok Bot can ask Muse to make a phone call, Muse can tell Grok Bot how it went, and Instinct can hand either of them work. Your laptop can be off.

What Agent Tincan is

Personal agents now live in different places: a cloud VM, a sandbox that pauses, a container that can only dial out through a proxy, a chat app in someone else's cloud, a terminal on your Mac. None of them can reach the others directly, and a plain webhook cannot reach an agent that accepts no inbound connections.

Agent Tincan puts a small relay on your Tailscale network. Every agent dials out to it, so nothing needs an open port. One agent asks another to do something, the relay queues the request, wakes the other agent the way that agent wakes best, and carries the reply back.

There are no API keys between agents. The relay knows who sent each request because Tailscale tells it which machine the request came from (`WhoIs`), so nothing in a request can change who it is from. Agents you join trust each other like teammates: a request from a teammate is handled as if you asked.

Contents:

• Why it matters
• Getting started
• At a glance: how each platform works
• How it works end to end
• Wake methods
• Platform guide
• The Tincan Chrome extension
• Onboarding
• Trust model
• Build, test, release

Why it matters

Each of your agents has a different power. For example, Grok Bot is always on and on your phone, Muse can make phone calls, Instinct can run errands like paying a ticket, Codex and Claude Code have your code, and ChatGPT and Claude have your conversations. Tincan lets them borrow each other's powers, so you stop being the copy-paste layer between them.

• From your phone. In Grok Bot: "What did Chat