Projects
Open-source tools and experiments grown from my own workflow.
Think with context you own.
SelfContext keeps the context you choose in portable Markdown and makes it available to the AI tool you already use, so useful conversations can continue from your history, goals, decisions, constraints, and evidence instead of starting from zero.
A practical reference for the tools around my development workflow.
A living collection of setup notes, configuration, and practical references for AI coding agents, developer environment utilities, and server infrastructure.
A practical starting point for running open-source models on Apple Silicon.
Guides and small helpers for MLX, llama.cpp, oMLX, and MTPLX: install a runtime, get a model, start the server, and learn the concepts as you go.
One focused ticket. One reviewable PR.
SWE Forge is an opt-in, harness-agnostic workflow for coding agents. It takes one focused coding ticket to one evidence-backed, reviewable PR through one writable delivery checkout. PR delivery is the default, and it never merges automatically.
Reusable capabilities for OpenCode, Claude Code, and compatible AI coding agents.
This repository collects focused skills that give AI coding agents reusable guidance for engineering, validation, and review work. Each skill is a small, portable package with a clear purpose, so it can be installed when useful instead of becoming part of every prompt.
A small local-first desktop app for understanding AI coding workflows.
Nano Harness is a personal, pre-release Electron app for working with AI providers under controlled autonomy. It connects provider adapters, workspace tools, approvals, runs, persistence, and inspectable evidence in one local desktop experiment.
Looking for prototypes and interactive experiments? Visit the Lab →