0-to-1 delivery, agent workflows, multimodal systems, retrieval, and cross-platform deployment — built with Python, TypeScript and AI coding agents.
feifei.rong2@gmail.comProcedural Graphs store steps, conditions, and common failure modes in a workflow that can guide long-horizon agents locally and improve through validation.
read note →How GPT-Live-1 handles speech, pauses, and interruptions in one model while delegating complex work to a backend model.
read note →Bypass Gmail's front-end UI limits and batch-mark thousands of unread emails via Apps Script, with rate-limit-safe pagination and progress logging.
read note →A small technical station for keeping the useful parts of ongoing work in public.
read note →Twelve communication tools—from reframing premises to calibrating uncertainty—visible in Dario Amodei’s answers to hostile questions.
read note →Technology needs high-level boundaries: a victory achieved by destroying the values being defended is not a meaningful victory.
read note →A node-based workflow platform for batch AI video production. I participate across the full delivery lifecycle and lead the initial workflow design.
An open-source ComfyUI canvas extension that keeps large workflows readable with one-click alignment, size normalization, graph-aware flow layout, color styling, and live previews.
An open-source AI maintainer for ComfyUI custom nodes that detects upstream compatibility risks, plans and tests adaptations, maintains issues, and opens evidence-backed draft pull requests.
An open-source Codex skill for context-health checks, cost-aware model and subagent routing, and evidence-preserving rotation across long AI coding sessions.