🧠 SDK
The Developer Platform for Robot Intelligence
Train, fine-tune, and deploy RL policies with one SDK. Local or cloud training, plug-and-play robot integration, and publish directly to the Model Hub.
Open source. Python-first. Production-ready.
How it works
Three commands from install to deployed policy.
Install & Connect
Authenticate with your account and connect your robot hardware or simulation environment.
$ ok auth loginTrain or Fine-Tune
Use a pretrained foundation model from the Hub as a starting point, or train a new policy from scratch with your task definition.
$ ok train --base humanoid-walk-v2 --task my_taskDeploy to Real Hardware
Push the trained policy directly to your robot with one command. Monitor performance and iterate without downtime.
$ ok deploy --robot spot --policy my_task-v1Everything you need to build robot intelligence
Train New Policies
Define your robot's task, connect your environment, and launch training. Works with captured real-world scenes or standard simulation environments.
Fine-Tune Foundation Models
Start from a pretrained policy from the Hub and fine-tune it on your specific hardware, environment, or task. Reduce training time from days to hours.
Local or Cloud Training
Train on your own GPU cluster or use our cloud simulation infrastructure. Spin up parallel training runs without managing infrastructure.
Plug & Play Integration
Connect your robot, sensors, and constraints in a few lines of Python. The SDK handles the interface layer for all major robot platforms.
Publish to the Hub
Push trained policies to the Model Hub as public or private repositories. Version, document, and share with your team or the community.
Continuous Improvement Loop
Collect new data from real deployments, retrain, and push updates — without manual pipeline management.
Built for your workflow
ML Engineers
Full control over training configs, reward shaping, and architecture. Integrate with your existing MLOps stack.
Robotics Developers
Spend time on robot behavior, not infrastructure. The SDK abstracts the RL training loop and hardware interface.
Research Labs
Reproduce published results, fork foundation models, and publish new baselines directly to the community Hub.
DevOps / Platform Teams
Deploy training jobs to cloud infrastructure with a single command. CI/CD pipelines for robot policies.
Start building robot intelligence
Get early access to the SDK and deploy your first trained policy to real hardware.
Request Early Access