Jie Xiang

Hi, I'm Jie 👋

I keep a commercial KVM cloud platform from falling over for a living. On the side I run a multi-agent Claude Code pipeline that has put 32 iOS apps on the App Store. I write here when something in either world surprises me — usually with a number attached.

NOW · week of Apr 22
  • Shipped claude-agent-ledger v0.4 — added --by project, found out 50% of my Claude Code spend goes to one codebase.
  • ShipReady v1.0 sitting in Apple review since Apr 19. PetBook v1.0.8 in queue too.
  • This site is the new public surface — built it Mon–Tue. The OG image is auto-generated; see scripts/og_image.py.
WHAT I SHIP
OPEN SOURCE SPOTLIGHT
v0.4.0 on npm · MIT

claude-agent-ledger →

Per-subagent · per-model · per-project · per-session · per-day cost attribution for Claude Code. Reads the local JSONL session logs and shows what each dimension actually consumed at marginal API rates. My own pipeline runs at ~$13K/week shadow cost on a $200/mo Max plan (~250× leverage) — the gap is the most interesting thing I've seen in LLM infra this year.

npm install -g claude-agent-ledger
agent-ledger week --summary
WRITING

All posts →

THE THESIS

AI Agents ship fast but break in the same long-tail ways distributed systems always have. Most teams don't yet have the eval, observability or reliability practices to catch it.

Six years of debugging a hypervisor at 3 AM gives you a reflex: if you don't have a per-component bill of materials, you don't actually understand the system. I'm pointing that reflex at AI Agents.

FIND ME

More about me →