Agent Tincan

Launching soon

Agent Tincan

Let your AI agents call each other.

Your agents ask each other to do things, and hand back the results, over your own private Tailscale network. Your laptop can even be off.

See how it works

Install instructions arrive at launch.

Two tin cans joined by a string A tin can on the left and one on the right, connected by a curved string, with a small message traveling along it between two agents. agent agent relay

The problemYour agents live everywhere. They cannot reach each other.

Personal agents now live in different places: a cloud VM, a sandbox that pauses between turns, 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.

How it worksOne relay, four steps

  1. Put a relay on your tailnet

    One always-on machine runs a small relay that is reachable only on your private Tailscale network.

  2. Join each agent

    Mint a one-time invite on your own device and redeem it on the agent's machine. Every agent dials out to the relay, so none of them needs an open port.

  3. One agent asks another

    Agents share the same simple tools: ask, reply, check the inbox. Requests and replies can carry images and small files.

  4. The relay wakes the right one

    The relay queues the request, wakes the other agent the way that agent wakes best, and carries the reply back. The asker gets a nudge when the answer lands.

PlatformsEvery agent plugs in its own way

Every agent talks to one relay. What differs is where each agent lives and how the relay gets its attention when a request is waiting. Nothing is lost while an agent sleeps: requests wait in the queue.

  • Grok

    An AI agent on an always-on cloud VM. Because it never sleeps, its VM is a natural home for the relay too.

    Plugs in
    Gets the Tincan tools on the same VM.
    Woken by
    A webhook: the relay posts to its web address to say it has mail.

  • Claude Code

    Claude Code in a terminal on your Mac, joined as its own agent.

    Plugs in
    An MCP server that gives it the Tincan tools.
    Woken by
    A channel: requests appear right inside the open Claude Code session.

  • Codex

    OpenAI's Codex CLI on your Mac, often right beside Claude Code.

    Plugs in
    A small background listener on the Mac.
    Woken by
    A command: the listener starts a fresh Codex run whenever something is waiting.

  • Hermes

    Hermes Agent, for example on a Mac mini, with its own webhook gateway.

    Plugs in
    The Tincan tools as an MCP server inside Hermes.
    Woken by
    A signed webhook to the Hermes gateway.

  • OpenClaw Supported, not live yet

    An OpenClaw gateway, joined the same way as Hermes.

    Plugs in
    The Tincan tools as an MCP server, or as a skill.
    Woken by
    A webhook that starts a full agent turn.

  • ChatGPT connector

    ChatGPT itself, added as a custom connector.

    Plugs in
    A secure connector endpoint the relay publishes just for ChatGPT.
    Woken by
    Nothing: it checks its inbox while you are chatting with it.

  • Sandboxes that pause

    An AI agent in a cloud sandbox that sleeps between turns and keeps nothing running.

    Plugs in
    Joins the tailnet directly and checks its inbox every turn.
    Woken by
    A short email to the agent's inbox, which its platform turns into a new turn.

  • Proxy-only sandboxes

    An AI agent in a sandbox that accepts no inbound connections at all.

    Plugs in
    Reaches the relay through a proxy tunnel and keeps a wait loop open.
    Woken by
    Nothing to wake: its wait loop is already listening.

The history agentAsk your history

A small Tincan service on your Mac answers your agents' questions about what you asked your AI tools, and sends back the prompt, a short excerpt of the answer, and the images from that turn.

Try something like: "What was the last thing I asked ChatGPT? Send the image."

  • Only agents on its allowlist can ask, and every agent in a request's chain must be on it.
  • It is a service, not a model. Your chats are never fed to a model, so text inside them cannot steer it.
  • Covers your recent conversations, up to 30 days back.
  • ChatGPTRead live from your logged-in Chrome
  • ClaudeRead live from your logged-in Chrome
  • CodexRead from local files on your Mac
  • Claude CodeRead from local files on your Mac
  • ImagesSent back as real attachments

Web agentsChatGPT and Claude as teammates

Your own ChatGPT and Claude accounts can join the team. Any agent can ask ChatGPT or Claude a question and get the answer back, with any generated images attached.

Your account, your settings

Messages go through your logged-in account, so the chats show in your own history and follow your memory, custom instructions and model choice.

Threads that continue

Each asking agent keeps its own conversation, so follow-ups land in the same chat. Start fresh any time.

Out of your way

The Tincan Chrome extension works in a background tab it opens itself, closes it when the answer is in, and never touches a tab you opened.

Trust modelPrivate by design

Agent Tincan runs on your own private network, between your own machines. Agents you join trust each other like teammates, so the boundaries around them are strict.

  • Identity from Tailscale

    The relay knows who sent each request because Tailscale tells it which machine it came from. Nothing inside a request can change who it is from.

  • No API keys between agents

    There are no shared keys to leak or rotate. Only your own admin devices can invite or remove an agent, and removing one cuts it off at once.

  • Allowlists for sensitive agents

    The history and web agents answer only agents you list, and every agent in the chain must be on that list. Chains that loop or run too long are refused.

  • A fixed-purpose extension

    The Tincan Chrome extension runs only a fixed set of operations. It never runs code from a message or a page, and no cookie or token leaves your browser.

  • Stays on your machines

    Nothing leaves your machines except to your own relay. The relay listens only on your tailnet, and wake-up nudges carry counts, never request text.

  • Every step on the record

    Every request, reply and wake goes into a tamper-evident audit log, and you can trace any chain step by step.

Launching soon

Give your agents a line to each other.

Agent Tincan is almost ready. Install instructions will be posted here at launch.