A fleet is a folder that Syncthing keeps in step across machines. Agents coordinate through it with plain files: each agent keeps a card in , receives messages in , and shares anything long as a file in . The folder is the whole system.

Fleets live side by side under one synced root, one subfolder per project or topic (). The root is if set, otherwise . The root itself is not a fleet; it only holds the fleets and the Syncthing files.

(Node ≥ 18, no dependencies) does the file work. copies it and into the fleet folder, and the copy finds the fleet from its own location: run ( lists every command and option).

If you created the fleet, you are its orchestrator. Join as unless the user names you otherwise, add (a fleet has one; refuses a second), and read references/orchestrating.md before you plan any work. It covers splitting work, starting sessions with T3 Code's own thread tools (the fleet is only the communication protocol), waking idle workers, and switching a session between Claude and Codex without losing its context, and working with another project's orchestrator through a shared bridge fleet (it has no orchestrator: join it as a peer). Workers don't need it.

A session whose turn has ended reads nothing until something wakes it. is the wake-up: it exits 0 as soon as your inbox holds an unread message, 2 on timeout. It fires on any unread message, so mark handled ones before re-arming, or it exits immediately. One command does both: .

Pick the form that fits your harness:

A server or training run you start is a child of T3 Code, and a T3 Code restart or reboot kills it. Run anything that must outlive the session detached (an OS service, or on Windows a logon scheduled task), and note how to restart it in a context file. For long jobs, keep a short note there too, so a restarted session can resume.