@harrisonguo

I Tested CodeGraph on Hono. The Tool-Call Savings Reproduce — the Cost Savings Don't.

2d ago · 18 min read · Two weeks ago CodeGraph hit GitHub trending — tree-sitter + SQLite/FTS5 + MCP for Claude Code, 19k+ stars in a week. The team published a benchmark on 7 repos showing 35% cheaper, 57% fewer tokens, 46

Agent Memory Is a Cache Coherence Problem

5d ago · 20 min read · This post is one half of a pair. The other half — Agent Retrieval Is a Cost Curve Problem — argues that Claude Code's within-session code retrieval avoids RAG because the cost curve says it should. Th

Agent Retrieval Is a Cost Curve Problem: Why Claude Code Doesn't Use RAG

May 26 · 27 min read · There's a popular interview question making the rounds: "Why doesn't Claude Code use RAG to retrieve code? Why grep?" The popular answer goes: chunking breaks code structure, vectors approximate when

Channels Aren't Message Passing — How Parked Goroutines OOM-Killed a Pod

May 14 · 18 min read · It's 3am. The Kafka consumer pod that's been running cleanly for six weeks gets OOM-killed. Kubernetes restarts it. Five minutes later: OOM-killed again. Restart. OOM-killed a third time. By the fourt

How I Improved an AI Agent from 40% to 60% — With A/B Test Data

May 12 · 7 min read · The Setup I was optimizing an AI agent for a production system — a creator agent that handles user requests like "make this character fiercer" or "rename this entity." The agent runs a 5-layer pipelin