Manage a fleet of AI agents

Fleet Control is an aeon skill: Operate managed Aeon instances from memory/instances.json - health-check, dispatch, and status snapshots (control), plus a fleet scorecard of runs, tokens, cost, and reliability (scorecard). Like every aeon skill it is one SKILL.md prompt file that runs unattended on your own GitHub Actions, on a schedule or when you trigger it, and sends what it finds to Telegram, Discord, Slack or email.

Every aeon skill takes one optional text input, var, set in aeon.yml or typed in when you run it by hand. It picks the target or the mode for that run.

Command / view selector. Empty (or unrecognized) → Health Check (default control view). status → full Status Mode (control view). dispatch <instance|*> <skill> [var=<value>] → Dispatch Mode: trigger a skill on one child or all healthy/degraded children (control view). scorecard → Scorecard Mode: fleet-wide runs/tokens/cost/reliability scorecard with day-over-day deltas + alerts (scorecard view).

Besides the model you connected to aeon, Fleet Control uses the following. Add secrets as GitHub Actions secrets on your aeon repo, or in Aeon Connect.

• GH_READ_PAT - optional secret, unlocks more data or features

Easiest: open Aeon Connect, sign in with GitHub and turn on Fleet Control. No clone, no terminal. To add it to an existing aeon repo from a shell, run:

Then switch it on in aeon.yml (the default schedule is filled in):

skills:
  fleet-control: { enabled: true, schedule: "0 9,15 * * *", var: "" }

New to aeon? Read the docs for how skills, schedules and memory fit together, or browse all skills.