devwithjevRobot Brain for Cube Stacking
The PyBullet robot uses Jev as a reflex layer that evaluates simulation states in <100ms to adapt. Claude generates the high-level plan to stack cubes.
View on X time<100ms
Jad Fayad@Jadfyd๐
Built a System 1 + System 2 robot brain using @typesafeai's Jev in PyBullet. ๐ง Claude: Generates the high-level plan to stack cubes. โก Jev: Acts as the split-second reflex layer, evaluating sim states in <100ms to adapt. Fast, schema-safe neurosymbolic robotics in action. https://t.co/WVNB1aqo7n
The author describes the setup as a System 1 + System 2 robot brain. They characterize it as fast, schema-safe neurosymbolic robotics.
Also filed under Robotics & devices
- Evaluates Machine Faults with Jev
The project replays compressor telemetry through an emulated device, uses code to flag suspicious behavior, and asks Jev to identify the fault described by a machine manual.
- Hand Gestures Control a Computer
Jev detects hand gestures and movement to control a computer in real time.
- MuJoCo Robot Decision Workbench
EmbodiedJev is a MuJoCo robot decision workbench with MiniCPM5-2B, Jev, and compatible model APIs.
- Jev Controls an xArm7 in MuJoCo
The MuJoCo xArm7 study has Jev choose movement directions and gripper actions from physical feedback.