Drive the agent¶
A live project runs an autonomous loop: the
agent proposes experiments, writes code, schedules runs, and analyzes results.
You stay in control of that loop from autolab status.
Where am I?¶
Shows the project at a glance — the agent state (live or paused), attached nodes, experiment counts, and the experiment you're in.
Start, pause & resume¶
autolab start # start the agent (first start takes the project live); resume after a pause
autolab pause # pause the loop — queued work waits, the agent stops acting
The first autolab start takes the project live — it seeds the baseline from
your code (or lets the agent author it for an empty project) and starts the
autonomous loop. After that, start simply resumes a paused loop.
Pausing is the safe way to make changes — edit settings, adjust the queue, or reassign keys — without the agent acting mid-change.
Automatic idea generation (autogen)¶
autolab status autogen # show the current agent + ideas state
autolab status autogen on # let the agent propose new experiments on its own
autolab status autogen off # only run what you queue
With autogen off, the agent still codes, runs, and analyzes — but it only works through experiments you submit. Turn it on to let it explore the search space autonomously. This is the core human-in-the-loop dial: tighten it when you want a hand on the wheel, loosen it to let Autolab run.
Queue your own work alongside the agent with
submit, and watch progress with autolab log and
autolab open.