Projects

Guided spec conductor: an assertive interview that turns a fuzzy idea, or a pile of existing code, into one agent-ready SPEC.md — by interrogating why, researching what you don’t know, and pulling in other models to attack your reasoning.

PostgreSQL wire-protocol codec, session pool, and socket helpers as a reusable Rust crate — the foundation layer extracted from pg-retest’s proxy for building a Postgres router.

Postgres-native agent-loop runtime in Rust. Invoke an LLM agent and its tool dispatch from SQL like a stored procedure — the agent reads and writes your tables directly, with a small trait-based kernel and everything else as a plugin.

The Rust performance line for pg-raggraph: a real pgrx extension with async background-worker ingest and hybrid retrieval, plus a sidecar mode for managed Postgres where you can’t load an extension at all.

Portable CLI for judging RAG and LLM benchmark runs across local, OpenAI-compatible, and cloud providers — a deterministic quick mode, a paraphrase-tolerant LLM-as-judge mode, and a full per-case audit trail for every verdict.

TDD/spec planner that turns product intent into small, deterministic Bob campaigns — one observable behavior per slice, with the verify command and scope caps frozen up front.

Apache AGE + pgvector in one PostgreSQL instance, side by side. Ask a question, watch vector-only, graph-only, and graph+vector retrieval run in parallel with timing for each.

Reads Claude Code’s own session transcripts and turns them into tokens, cost, time, and per-skill behavior — which prompt or skill is quietly ballooning your context, and which one keeps asking you questions.

Autonomous build → verify → judge loop. Bob drives a coding CLI in an isolated git worktree, gates the result on your own test command, and only applies the change once it converges.

A library of opinionated Claude Code skills, rules, agents, and slash commands that turn an AI coding session into an actual workflow — scope before planning, research before content, tests before claims, evidence before opinions.