I'm Byoungwook Kim — AI engineer at Runbear, creator of AutoRAG (★4.9K), the open-source framework that finds the optimal RAG pipeline for your data. I work on retrieval, evaluation, and AI safety — and I write about all of it.
Frameworks and tools used by engineers around the world.

RAG auto-optimization framework. Finds the best pipeline for your data — parsing, chunking, retrieval, and generation — automatically.

Prompt engineering project that pushed an LLM from top 22% to top 5% on the Korean SAT. Research collaboration with NIA Korea.

The awesome list of Korean LLMs — the reference collection for the Korean LLM ecosystem.

Advanced RAG framework for building reliable, high-performance retrieval pipelines.
Paper reviews, RAG experiments, and open-source stories.
Browse the full archive.
I believe the best AI is built in public. At Markr.AI I co-led the open-source projects that became AutoRAG — designing the framework, researching chunking and LLM-as-a-Judge evaluation, and growing a 500+ member community. Before that, I co-founded two startups: AutoRAG Inc., to commercialize the framework, and EDAI, an in-game advertising SDK with a granted patent.
Today I build AI teammates at Runbear and co-run NomaDamas, an open-source AI hacker house in Seoul. I teach what I learn — on stages like AWS Gen AI Loft and GDG DevFest, and in a Fast Campus course on RAG evaluation.