Projects
A smaller proof map for AI product engineering.
This page is intentionally filtered. The point is not that I have many repos; the point is whether a few pieces of work prove product judgment, agent architecture, enterprise interface taste, and open-source execution.
Featured proof
Six things I would show first.
2026 / public repo
炼云小说工厂
open-source May 2026 releaseAn open-source AI web novel production workbench with agent workflows, prompt management, living story documents, batch jobs, and run tracing.
2026 / sanitized work sample
Enterprise AI Console Case Study
sanitized engineering case studyA sanitized reconstruction of CDN console, AI gateway, log search, async task, and internal operations work where dense configuration needs safe, inspectable UX.
2026 / public fork
OpenClaw Contribution Fork
upstream proxy fix and contribution forkA focused OpenClaw contribution fork used to reproduce and patch a Feishu/Lark websocket proxy routing bug, then hand the proof back upstream.
2026 / public repo
Obsidian LLM Wiki
knowledge workflow experimentA lightweight knowledge-base experiment around Obsidian-style notes and LLM-readable personal memory surfaces.
2025 / public repo
YouChannel
public product prototypeA YouTube-centered AI product experiment with a public web surface and companion service repo for video-aware workflows.
2025 / public repo
MinIO Web UI
storage console explorationA Vue-based object storage UI exploration around bucket browsing and storage-console workflows.
Evidence gap closed
The enterprise console claim now has a public shape.
I cannot publish employer screenshots. I can publish the operating pattern: dense configuration, async tasks, logs, review states, rollback paths, and AI gateway permission boundaries in one inspectable workflow.
Read the sanitized case study- 01ConfigureCDN route or AI gateway rule
- 02ReviewDiff, rollout scope, permission boundary
- 03ExecuteAsync task, status, retry, rollback
- 04ObserveLogs, metrics, failure reason, owner