AI/ML Projects

26m function call model that runs on incredibly small devices

State-of-the-art TTS model under 25MB 😻

Fast and Accurate Code Search for Agents. Uses ~98% fewer tokens than grep+read

Semantic search over videos using Gemini Embedding 2 or Qwen3-VL.

Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces

On-device, real-time multimodal AI. Have natural voice and vision conversations with an AI that runs entirely on your machine. Powered by Gemma 4 E2B and Kokoro.

Talk to your Mac, query your docs, no cloud required. On-device voice AI + RAG

Fine-tune Gemma 4 and 3n with audio, images and text on Apple Silicon, using PyTorch and Metal Performance Shaders.

Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).

Web playground to create Gaussian Splats using Apple's SHARP model

TurboQuant WASM SIMD vector compression — 3 bits/dim with fast dot product. Requires relaxed SIMD (Chrome 114+, Firefox 128+, Safari 18+, Node 20+)

Gemma Gem runs Google's Gemma 4 model entirely on-device via WebGPU — no API keys, no cloud, no data leaving your machine.

Deterministic browser automation. Works out of the box with Claude/Codex/OpenCode

Browser Harness | Self-healing harness that enables LLMs to complete any task.

Biologically-inspired memory for AI agents. Decay, retrieval strengthening, consolidation. Zero dependencies.