Tutorials

Free TierEvery new account starts on a free tier with credits to call the SDK — no billing details required.Create API key →

Pick a Tutorial

Pick the one that matches your requirements. Each takes only a couple of minutes and ends with a working Skill result shown in Rerun.

Robotics

Set Cartesian Pose

Drive a manipulator of a brand of your choice along a closed Cartesian trajectory. No real or simulated robot needed.

Jump to tutorial →

Robotics

Set Joint Positions

Drive a manipulator of a brand of your choice to a target joint configuration and watch the trajectory play out in Rerun. No real or simulated robot needed.

Jump to tutorial →

2D Vision

Image Foreground Segmentation

Run BiRefNet on a sample image and see the foreground mask in Rerun. No clone, no hardware.

Jump to tutorial →

3D Vision

Point Cloud Voxel Downsampling

Build a dense synthetic point cloud, merge points with a voxel grid, and view input vs output in Rerun. No clone, no hardware.

Jump to tutorial →

Hardware

Capture from a Webcam

Connect to a USB webcam, capture a frame, and view it in Rerun. Requires any USB camera.

Jump to tutorial →

Where to Go Next?

Ready to go deeper? Browse the Telekinesis Skill Examples repository for a runnable example covering every Skill.

Skill Examples

One runnable example per Skill, across vision, 3D, hardware, and robotics.

Explore the Docs

Skills

Vision, 3D, hardware, and robotics skills — the full API reference.

Agents

Turn natural-language instructions into robot code with Tzara, the VS Code agent.

Data Engine

Generate and manage synthetic datasets for training Physical AI models.

BabyROS

Lightweight pub/sub and service primitives for building robot communication layers.

Applications

Real-world use cases: pick-and-place, palletizing, quality inspection, and more.

Support

Join Discord

Ask questions, share what you're building, and get help from the community.

Add a Skill?

Have a new Skill to be added to Telekinesis? Get in touch with us.