LLM Doctor
A PyPI package that diagnoses broken LLM-analytics ingestion into PostHog — names the exact failure mode, then repairs spans in flight.
Products
Open source, shipped.
Tools I built because I needed them, then published because someone else will too. Everything here is public code you can install today.
Featured · Live on WordPress.org
Mokhai — Agent Readiness Kit
Make your site legible to AI agents: a clean Markdown twin of every page (50–100 KB of themed HTML becomes 4–8 KB of pure content), a curated /llms.txt with per-page descriptions, MCP-exposed operations, and a 0–100 Context Score. Free, GPL, no hosted backend.
Shipping · Ships as a CLI
TriageFast
Automated support-triage that converts chaotic inboxes into structured signals. Clusters by intent, surfaces verified bugs, and routes issues to the right owner — open-source, on your own infra, with no hosted backend.
-
-
evalspec
Gold-label evaluation for LLM agents — define correct behavior per question, measure what the model actually did, gate regressions in CI.
-
RAG Probe
A RAG evaluation harness that tells you whether retrieval, chunking, or generation failed — before you blame the model.
-
PHP AI Client
One clean PHP interface to LLM APIs — my contribution as part of the WordPress Core AI Team.