Projects
A snapshot of the things I'm lucky to work on. Most are open source; the rest will be when they're ready.
AI Builder
- SkillsBenchA benchmark for evaluating how well AI agents use skills.
- first-treeA Git-native context layer for decisions, ownership, and shared team knowledge.
- DoWhizAgent-native product for getting work done across email, chat, documents, and related tools.
- DeepTutorAn AI research assistant built on Zotero for cited answers, figure and formula understanding, and multi-paper comparison.
- mewsLocal GitHub notification daemon that triages your inbox and dispatches Codex or Claude Code work for allow-listed repos while you sleep.
- smolclawSeeded mock environments for testing agent behavior in realistic workflows.
- SBTI CLIAn offline CLI for testing agent behavior with bundled logic and exportable results.