Skip to main content
Megan makes your robots self-learn — on the edge, in the environment, as they run. You ship a robot with a frozen, well-trained policy. Then the world moves: a new obstacle appears, the dynamics drift, a disturbance starts hitting on a rhythm. A frozen policy can’t cope with what it never saw. Megan lets the robot learn its way through it on-device — the way a person adjusts on the job — with no retraining run, no labels, and no human in the loop.
Megan is a steering token that rides on top of your existing policy and adapts it only through governed changes. It never retrains your model wholesale and never touches actuators directly. It watches the task unfold, decides whether and where to change, and commits a change only if the robot measurably did better — otherwise it rolls back. That governance is what makes learning in the wild safe.

Learning like a human, on the edge

  • On the edge. The decision path is torch-free and runs on the robot (Jetson-class hardware). No cloud dependency at runtime.
  • In the environment. Adaptation happens while the task runs, against the real world in front of the robot — not offline on a dataset.
  • Self-supervised. Reality supplies the labels: the robot predicts what comes next, and the world delivers the real next state a moment later. The gap between the two is a genuine learning signal — no annotation needed.
  • Governed. Every change is gated: keep it only if it helped and stayed stable.

How it knows it’s actually learning

Megan doesn’t change things and hope. It measures a few simple signals every round (this is what the megan-cd engine tracks under the hood) and only commits a change that improves them:
The governance is commit-or-rollback: a change is applied only if it measurably improved and the outcome stayed stable within tolerance; otherwise it’s reverted. In a controlled test where the world’s dynamics shifted mid-deployment, a frozen model’s skill collapsed to 0.66worse than assuming the world had frozen — while Megan brought it back to ~2.6, recovering online in a couple of adaptation steps. Honest, partial, real recovery — not a staged demo.

The four ways a robot self-learns

Everything Megan does falls into four capabilities. Each optimises one of the signals above.

1 · Anticipation — learn a rhythm and act before it hits

Some disturbances recur on a beat — a conveyor bump, a gust, a load that shifts every few seconds. Megan learns the rhythm from the times it happens, then tells the robot to protect ahead of the next hit and which protective action is currently best. The robot stops reacting late and starts anticipating, the way an experienced worker braces before the machine kicks.

2 · Finding ways around obstacles — route when the plan is blocked

When the frontier of a task is blocked, a frozen policy pushes into the wall. Megan watches progress toward each milestone and, the moment the current plan stops working, routes the robot to adapthere — so your change-doer can find a way around instead of stalling. It’s the difference between a robot that gives up at an obstacle and one that works out a detour.

3 · Becoming more efficient — get faster at what it already does

Once a task reliably succeeds, Megan makes it faster, one committed step at a time — nudging the slowest part quicker (or dropping a redundant step) and keeping the change only if the outcome still lands within tolerance. Over repetitions the robot sheds the caution it needed while learning and settles into a smooth, efficient routine — exactly how a human speeds up with practice.

4 · Fixing an execution shift — correct a miscalibration on-device

When the robot’s actuator is miscalibrated — every commanded direction applied rotated by some unknown angle it never trained on — a frozen policy drives confidently the wrong way forever. Megan searches a corrective action-frame rotation from the real progress signal, keeps the one that resumes progress, and carries it across episodes — so the same frozen policy recovers itself, with no labels and no retraining.

The locked contract

Megan returns only the actionable decision — never the internals it used to reach it.
Responses carry route + frontier (sessions), should_protect + best_action + ready (anticipators), and phi (governors) — and nothing else. The progress metric, stall counters, the blocked flag, the bandit’s per-candidate values, the learned rhythm’s period/phase/confidence, and the reasoning trace all stay on the server. The routes are also rate-limited per account so the decision boundary can’t be reconstructed by probing.
You integrate against a stable, minimal decision surface, and the valuable self-learning mechanism can’t leak out of a response.

Two ways to reach it

Next

Setup

Install the SDK, get your key, make your first call.

Build deep

Wire self-learning into a real control loop.