• 001

  Echoes

  Real-time multimodal medical interpreter for clinical settings. Patients speak in any of 40+ languages — Echoes transcribes, translates, watches for visible distress via camera, flags life-threatening symptoms, and suggests triage follow-ups. Built for the Gemma 4 Good Hackathon (Kaggle × Google DeepMind).

  Next.jsPythonFastAPIGemma 4ModalvLLM
  View ↗
• 002

  WikiMind

  Personal knowledge base builder — upload PDFs, Markdown, plain text, or a ChatGPT/Claude export ZIP and an LLM incrementally compiles a structured, cross-linked wiki from them. Workspace data stored in Supabase; backend on Render; frontend on Vercel. Total hosting cost $0.

  Node.jsNext.jsSupabaseLLMVercel
  View ↗
• 003

  DriftScope

  Local-first Python library for detecting semantic drift in LLM outputs. Wraps model calls, stores prompts and responses in SQLite, embeds outputs locally, and alerts when later outputs move outside a calibrated baseline — no cloud account required.

  PythonSQLiteEmbeddingsLLMObservability
  View ↗

Feel free to reach out.