All projects
  • DeepNeuron · Team

Omni AR

An AR assistant that watches a scene, remembers it, and answers questions about it later. Built for everyday recall, and for people living with memory impairment.

Stack

  • Python
  • Flask
  • React
  • Gemini Vision
  • Whisper
  • SSE

Links

Source

What I built

  • A hand-rolled vector memory store with normalized cosine similarity, time-windowed recall, and disk persistence.
  • A low-latency streaming voice pipeline: Whisper → Gemini intent router → sentence-chunked parallel TTS over SSE, tuned for time-to-first-audio.

TODO(content): full case study (problem → approach → outcome) coming. The card metadata above is migrated verbatim from the live site.