Research, releases, and field notes.
Open benchmark
robot-eval-bench
Product · Sep 29, 2026
Introducing RL runs: train robot policies in simulation from the API
Send a task spec, get back a trained policy: ONNX, the MuJoCo scene it trained in, clips, and a verdict from measured checks. One real run, from request to walking robot.
Read article
Latest
Day to night: relighting a robot dataset with the Kite API
Product·Oct 5, 2026
Simulating cardboard boxes that behave like cardboard
Research·Oct 3, 2026
Introducing Kite Evals
Product·Aug 14, 2026
Two new judges on robot-eval-bench: Gemini 3.7 flash and Muse Spark 1.1
Research·Aug 13, 2026
Cornucopia Bio ships lab automation policies in hours, not weeks
Customer Stories·Aug 10, 2026
Robot-eval-bench: Benchmarking task success evaluation for VLMs
Research·Jul 30, 2026
Introducing the Kite Platform API
Product·Jul 29, 2026
The evidence for data augmentation in robotics
Research·Jul 28, 2026
Kite joins the NVIDIA Inception Program
Company·Jun 10, 2026