Projects

Current Projects

Gaze

Test quality analysis via side effect detection for Go. Gaze detects every observable side effect a function produces, classifies each effect as contractual or incidental, and measures whether your tests actually assert on the things that matter. It introduces three metrics – Contract Coverage, Over-Specification Score, and GazeCRAP – that go beyond line coverage to reveal the real quality of your test suite.

Dewey

Semantic knowledge retrieval for AI agents. Dewey combines structured graph traversal with vector-based semantic search to give every hero in the swarm cross-repository context – local files, GitHub issues, and web documentation searchable through a unified MCP interface. Dewey enables autonomous specification drafting, reducing human checkpoints from two to one.

Replicator

Multi-agent coordination for AI coding agents. Replicator provides 53 MCP tools for work tracking, parallel orchestration with git worktrees, file reservations, and semantic memory – all in a single Go binary with zero runtime dependencies. Install via Homebrew and connect any MCP-compatible AI agent.