Robotics and devices

Put Jev in the middle layer between perception, intent, and a physical action.

Robotics and devices·Showing 9 of 420 entries

All builds

ラプター | ロボコンビジコン

@Raptor_zip

ラプター | ロボコンビジコン

XRobotics and devices

A dual-arm robot with Jev in the middle layer

Response: ~500 ms
Cost per attempt: ~¥0.5

Aditya Singh

@xyz04274951

I made this for fun. Wired a mic over Fusion 360: click, speak, Fusion runs the feature. @typesafeai ‘s Jev only decides if the utterance is a command.

XRobotics and devices

Voice control over Fusion 360

GitHub·Robotics and devices

@GitHub·Robotics and devices

GitHub·Robotics and devices

XRobotics and devices

jev-drone

GitHub·Robotics and devices

@GitHub·Robotics and devices

GitHub·Robotics and devices

XRobotics and devices

EmbodiedJev

GitHub·Robotics and devices

@GitHub·Robotics and devices

GitHub·Robotics and devices

XRobotics and devices

RoboJEV

GitHub·Robotics and devices

@GitHub·Robotics and devices

GitHub·Robotics and devices

XRobotics and devices

home-assistant-typesafe

GitHub · Robotics and devices

Pick

JevArm: 6-DoF Manipulator Intent Gate

Physical computing project embedding Jev as an intermediary state arbiter between vision cameras and robotic arm trajectory planning.

Decision

Select the optimal grasping orientation based on bounding box point cloud.

16.6 ms cycle · 60 Hz loopSource

GitHub · Robotics and devices

Voice-to-Intent Pipeline (Whisper + Jev)

Speech interface translating live microphone stream to typed hardware controls in under 80 milliseconds without waiting for an LLM answer.

Decision

Map speech audio transcription to discrete device command opcode.

72ms total latencySource

GitHub · Robotics and devices

Pick

Android On-Device Jev Runtime

Quantized INT8 decision model running natively on Snapdragon NPU hardware inside an Android service without internet connection.

Decision

Classify user screen state for accessibility voice navigation.

14ms on Snapdragon 8 Gen 3Source