Skip to main content

Physical AI · Build in Public

VAJRA — autonomous find-and-fetch robot

Jetson Orin Nano + ROS 2 + NanoOWL. Under construction. Same governance instincts as Agentify (deny-by-default, budget routers, eval harnesses) re-applied to physical actions.

Demo · Coming Soon

Tabletop "fetch the red mug" demo

15-second autoplay loop lands here once the v0.1 milestone clip is recorded — actively in build. Tracked in the status checklist below.

Hardware stack

  • Compute: NVIDIA Jetson Orin Nano Super (8 GB)
  • Locomotion: Differential-drive base (mid-build)
  • Manipulation: 5-DOF arm + parallel gripper (sourced)
  • Sensing: RGB camera, IMU; depth sensor planned
  • Compute budget: ₹35–45K total component spend

Software stack

  • OS / middleware: Ubuntu 22.04 + ROS 2 Humble (Jazzy migration in progress)
  • Perception: NanoOWL (TensorRT-optimized OWL-ViT) — open-vocabulary detection
  • Foundation reference: NVIDIA GR00T N1.7 + Cosmos 3 (April 2026 release)
  • Navigation: Nav2 stack — costmap + behavior tree planner
  • Governance: Capability-lease envelope per action (deny-by-default)
  • Telemetry: OpenTelemetry → Datadog; budget routers per task class

Status

Honest checklist — anything not in green is intent, not capability.

  • Hardware sourced; Jetson Orin Nano boots.
  • NanoOWL TensorRT engine threshold-tuned.
  • Object recognition demo on tabletop scene.
  • ROS 2 nodes for locomotion + manipulation (in progress).
  • End-to-end "fetch the red mug" demo recording.
  • Public Discord with weekly office-hour build session.

Build log

Public, dated, append-only on GitHub. No demo cuts, no marketing lift.

Last updated 2026-04-27.