projects
Twelve systems, eleven in the open.
An AI harness for VS Code, an open-weight decision model, on-device LLM inference, RAG pipelines, multi-agent systems and the MLOps that keeps them honest - each with a write-up of the problem, how it works, and why it exists.
Omnitron - AI coding agents in your own workspace
My build of DeepSeek Harness, the open-source platform for running AI coding agents in your own workspace: one plugin core behind a web UI and a desktop app for Linux, macOS and Windows, released as Omnitron 1.0 with its own identity, interface and operational guards.
Tron-1B - A fast, open-weight decision model
An open-weight 1.1B decision model with its own runtime and decision head. It answers choice, rating and yes/no questions with calibrated probabilities in about 17 ms, and beats Jev 1.13.0 on all four of its published benchmarks (average 90.1 vs 74.7). It improves itself nightly from a larger model's labels.
Wayne - AI harness for VS Code
An AI harness living in the IDE - it plans before it codes, reads the codebase and follows call sites, runs commands and reacts to failures, and presents every change as a diff you approve. Extends through MCP. Live on the VS Code Marketplace.
PrometheusAI - Offline LLM assistant for Android
On-device inference with zero cloud dependency. Runs LLaMA 3.1, IBM Granite, and Mistral via 4-bit GGUF at ~8 tok/s, with on-device RAG over your own documents.
tokenash - Local-first context compression
Context compression for LLM applications that runs locally - 50–90% fewer tokens for the same answers, with nothing shipped to a third-party service to get there.
HLST - Long-context LLMs on edge
Reference code for my TechRxiv preprint: hierarchical latent state-space recurrence that democratises long-context LLMs on edge devices, as a transformer alternative.
KCD New York 2026 - Production RAG on Kubernetes
Demo from my KCD New York 2026 talk - deploying, autoscaling, and observing production RAG pipelines on Kubernetes with vLLM and vector search.
Apache Beam Summit 2026 - Real-time AI pipelines
Embedding LLMs and RAG directly into Apache Beam transforms for low-latency inference on high-velocity data streams.
Relay - Open-source outbound agent
An open-source AI agent for outbound leads - the research, qualification, and follow-up loop handled by a tool-using agent rather than a sequence of manual steps.
Franola - Open-source AI note-taking
An open-source AI note-taking app in the Granola mould, written in Rust - meeting notes captured and structured by a model, without the notes leaving a proprietary product.
GateKeep - Agentic personal finance
An agentic-AI finance tracker that ingests transactions and reasons over them with tool-using agents to surface spend insights.
AIORNOR - AI-or-human text detection
Detects whether a piece of text is AI-generated or human-written using a perplexity-based metric, served through a lightweight web app.
Hiring for AI or ML?
I am open to AI/ML Engineering, Data Science, and Python roles, plus research collaborations and consulting. New York based, shipping worldwide.