Work
A focused list of work with public proof: repositories, write-ups, live links, or enough context to understand what was built.
AI risk evaluation
A lightweight evaluation workbench for comparing open-source and frontier AI assistants before enterprise deployment.
Surfaces real differences between model backends with structured CSV results, one-page PDF reports, and auditable risk findings across hallucination, bias, jailbreak resistance, and cost.
LLM evaluation
A public JavaScript project for testing language models against adversarial prompts and safety-focused evaluation cases.
Useful because it turns model-safety questions into repeatable prompt runs instead of one-off screenshots.
Automation plugin
An OpenClaw plugin for fetching and analyzing GitHub issues, built from the hackathon work I wrote about.
Shows the practical direction of the site: reducing repetitive project work with AI-assisted tooling.
AI workflow
A dashboard and CLI workflow for syncing Gemini CLI conversations across devices.
The public README documents cloud sync, per-project sync, copyable commands, and automatic resume behavior.