Agent Tincan: open-source relay lets AI agents ask each other for help over Tailscale
Saboo_Shubham_ · x · 2026-09-27
agent-tincan, an open-source project by mvanhorn, lets personal AI agents scattered across environments collaborate — GrokBot can ask Muse to place a phone call, Muse reports back how it went, and Instinct can hand work to either. It works even when your laptop is off.
The problem it solves: personal agents now live in cloud VMs, pausable sandboxes, containers that only dial out through a proxy, chat apps in someone else's cloud, or a Mac terminal. None can reach the others directly, and plain webhooks can't reach agents that accept no inbound connections.
The design: Agent Tincan runs a small relay on your Tailscale network. Every agent dials out to it, so no ports need to be open. One agent asks another to do something, the relay queues the request and wakes the target agent the way that agent wakes best. Fully open source.
Related event: Open-Source Tools Let Distributed AI Agents Collaborate(2 posts)→
More from coding & agent
- Meta's Muse gives every user their own VM, called the most careful consumer agent sandbox yet — AccBalanced · 2026-09-27
- SafeScript: a Turing-incomplete JS subset lets agent policies replace code review — uriwa · 2026-09-27
- Open source AI-SQL engine Quail signals shift toward cheap task-specific models — sh_reya · 2026-09-27
- Life hack: run Claude Code with --dangerously-skip-permissions at / to free disk space — Kuprel · 2026-09-27
- Bend: a language that blocks AI coding mistakes with Lean-style proofs at C speed — arthurcolle · 2026-09-27
- Claude generates 177GB of temp files in a day, fills developer's entire disk — banteg · 2026-09-27