codebase-rag
A Python RAG system for chatting with codebases: chunking source code into a vector store, then using LLMs for semantic search and natural-language Q&A over code.
PythonRAGLLMVector Search
Roy Zhu · Waterloo, ON
Big systems taught me to build small ones.
Seventeen years of commerce, gaming, and platform engineering, from Beijing-scale distributed systems to a single SQLite file. Now consulting from Waterloo, learning every new field the same way: build something real, find where it breaks, write down what holds up.
Featured Projects
moziBot
A TypeScript multi-channel AI agent runtime: Telegram and Discord connected to one runtime with session persistence, task scheduling, job resumption, and structured observability.
TypeScriptAI AgentsNode.jsTelegramDiscord
Recent Posts
Concurrency in Local-First AI: Making SQLite Multi-Agent Safe
Updated: at 08:00 AMHow to fix SQLite database locks when multiple AI agents write to memory simultaneously, using WAL mode, threading.local, and application-layer RLocks.
Graph Traversal Without a Graph Database: BFS in Pure Python
Updated: at 07:00 AMWhy Neo4j is overkill for a personal AI agent's memory, and how to implement fast, multi-hop context retrieval using BFS in pure Python over SQLite.
Building a Deduplication Pipeline for Local Knowledge Graphs
Updated: at 06:00 AMWhy LLM extraction fails at knowledge graphs, and how a cascade of exact aliases, embeddings, and string fallback keeps local SQLite graphs clean.
Setting Up a Python Project Skeleton That Scales
Published: at 09:00 AMHow membox chose its libraries, organized its modules, and used typing.Protocol to keep the core dependency-free while staying testable and extensible.