Work
Things I've built, mostly real-time voice and LLM systems. Each one links to its source on GitHub.
- 2026Prep: voice coding copilotGitHub ↗
An interview-prep IDE with a voice: a Monaco editor, a LeetCode-style problem library, and an AI copilot you can talk to, interrupt and point at your code.
Voice AI · Electron · Monaco · LLM agents · TypeScript
- 2026Agent2DBGitHub ↗
A desktop database agent: connect PostgreSQL, ask in plain language, and let an agent explore the schema, write and run SQL, and remember what it learns, with a human approving every write.
Agents · LangGraph · PostgreSQL · Electron · MCP
- 2026voiceAgentGitHub ↗
A fully local, real-time voice assistant you can talk over: Parakeet listens, an LLM thinks, Kokoro speaks, SQLite remembers. Sub-second speech-to-speech with two-stage barge-in.
Voice AI · Speech recognition · TTS · LangGraph · Python
- 2026InterviewPracticeAIGitHub ↗
Voice interview practice: a Next.js app, a Node voice gateway running the turn-taking loop, and a Python "ear" doing VAD, end-of-turn detection and transcription on the GPU.
Voice AI · Next.js · WebSockets · Python · Testing
- 2026Karate 3D Avatar StudioGitHub ↗
Turn any video into an interactive 3D avatar: detection, camera estimation and SAM 3D Body mesh recovery, with a Three.js studio for labelling techniques and voice control.
Computer vision · 3D · SAM · Three.js · Python
- 2025Qwen3 Reranker APIGitHub ↗
A standalone, GPU-accelerated reranking service using Qwen3-Reranker-0.6B behind a Cohere-compatible /v2/rerank endpoint, so RAG pipelines can swap a hosted reranker for a local one.
RAG · Reranking · Python · Self-hosted models
- 2025Kokoro TTS APIGitHub ↗
A self-hosted, OpenAI-compatible text-to-speech server built on Kokoro, with robust text processing and 28 voices. Plugs straight into the Read Aloud browser extension.
TTS · Python · Self-hosted models · Accessibility