For the past few weeks I've been building Dynobox - a local test runner that records what an agent does inside a harness (Claude Code, Codex, OpenCode etc.) and lets you write deterministic assertions against its non-deterministic behavior: tool calls, shell commands, files created or changed and so on.
Mobile app automation and verification for AI coding agents. CLI, MCP server, and typed Node.js API for iOS, Android, HarmonyOS, TV, web, macOS, and Linux.
Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior.
A skill creator that proves its skills work. Evidence-driven skill creation for Claude Code and Codex: baseline-tested generation, per-skill regression evals, ecosystem doctor, cross-runtime compile, and an opt-in proactive advisor.
An occasional email when notable AI dev tools and models land in the directory. No spam, unsubscribe anytime.
