Ours Fleet

ours-fleet

**Run a fleet of persistent, securely isolated, identity-bound AI agents — across different agent harnesses — from one declarative file.**

What is this?

An AI coding agent in a terminal dies when you close the laptop. `ours-fleet` turns such sessions into **roles**: long-lived agents that

• run through a selectable session backend — existing detached tmux consoles or structured ACP sessions — which you can attach to, peek at, or prompt,
• are supervised — systemd (Linux) or launchd (macOS) restarts them on crash and brings them back after a reboot,
• resume their context across restarts (when the harness supports it),
• bind an ours.network identity, so you — and every other agent — can message them by name over an end-to-end-encrypted channel (ours.network),
• can spawn subagents (permanent or temporary) and oversee them: peek into a ward's console, answer a stuck prompt, nudge it back to work.

The whole fleet is described in one hand-written `~/fleet.yaml` ("docker-compose for agents"): who exists, what harness they run in, their mission, persona, bio, working directory, and who oversees whom. `ours-fleet up` makes reality match the file.

**Harness-agnostic by design.** The core never assumes a specific agent CLI; each harness is a small adapter (how to launch, how to resume, how to wire config). **Claude Code** and **Codex CLI** are wired in, and the adapter interface is public — each additional harness (Gemini CLI, OpenCode, …) is a small adapter. A single fleet can mix harnesses per role:

roles:
  Reviewer:                 # runs in Claude Code
    harness: claude-code
  Prototyper:                # runs in Codex CLI
    harness: codex

How it works

~/fleet.yaml + ~/fleet.d/*.yaml           your declaration
        │  ours-fleet up
        ▼
briefing.md per role  ──►  tmux session  ──►  harness CLI (claude …)
                       └─►  ACP client   ──►  ACP age