Started with cameras, drones, and DaVinci Resolve. Now I build AI products, agent infrastructure, and tools that have to survive contact with real devices and real workflows: phones, watches, Windows, creator pipelines. I care less about demos than whether the thing still works after deployment, user input, and edge cases.
Yoru Studio — A self-hosted execution studio for solo creators: projects, storyboards, field work, retrospectives, backups, and MCP-connected AI agents.
Akari Pulse — Reverse-engineered health data off a vivo WATCH GT. The official path won't export it, so: watch RPK → phone APK → own database → MCP.
Listening Bridge — Gives an AI fresh listening context from Android or Windows: active track, synced-lyrics context, and explicit playback controls over MCP.
is-ai-down — "Is it just me?" One page. Status + reachability probes on Cloudflare. Live.
chatgpt-mcp-connect — Verified ways to get custom MCP servers into ChatGPT, including direct servers and runtime/aggregation setups.
Claude Desktop Kill-Switch — Caught Claude Desktop connecting directly 25 times in 12 seconds when the proxy dropped. Fail-closed firewall rules, plus the six "fixes" that looked right and weren't.
Blender Story Video — Agent Skill: one idea → 4K H.265 through Blender + Resolve, with delivery checks for frame count, encoding, and checksum.
- Operit — Android AI agent · 20 merged PRs: model/provider integration, tool-call and history correctness, Compose/DSL state & timing, crash and UX fixes
- gzh-design-skill — WeChat editor clipboard serialization fix (#19)
- OpenCLI — Codex Desktop CDP adapter (#2281)
- open-kimi-ppt-skill — browser launch + download race fixes (#5, #6)