Skip to content
View vkehfdl1's full-sized avatar
:electron:
:electron:

Highlights

  • Pro

Organizations

@Whew-AI-Inc

Block or report vkehfdl1

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
vkehfdl1/README.md

Hi there 👋 I'm Jeffrey Kim (Dongkyu Kim) and I am open-source addict. Currently crazy about building things.

  • 🔭 I was leader & maker of AutoRAG, which is RAG AutoML tool. (4.5k+ Github Stars⭐)
  • 🍙 I am a leader of NomaDamas, which is an open-source AI HackerHouse in Seoul backed by Markr AI.
  • ✏️ I am a research intern at the KAIST AI DAVIAN lab.

💼 Projects

  • AutoRAG - AutoML tool for RAG. (4.5k+ Github Stars⭐)
  • AutoRAG-Research - Automate your RAG Research.
  • k-skill - A Korean automation skill collection for coding agents, covering SRT, KTX, KBO, subway arrivals, lotto checks, and more.
  • dani - A GitHub webhook to OMX automation loop for issue, PR review, approval, and auto-merge workflows.
  • slides-grab - Select context for agents directly from AI-generated HTML slides
  • ios-moaki - Moaki keyboard in iOS for Korean.
  • Noise-Cancel - Semantic filter for your LinkedIn Feed 🎧
  • AutoRAG-data - Tauri app to build Multi-modal RAG evaluation dataset.
  • KoDarkBench - Korean version of Dark Bench. Analyze the dark patterns of K-LLMs.
  • ClueHunter - Chrome extension to find the evidence from the cited webpage automatically.
  • awesome-korean-llm - Awesome list of Korean LLM models.
  • KICE-slayer-AI-Korean - Prompt Engineering for solving KSAT (수능) Korean problems.
  • RAGchain - Building advanced Document Q&A framework. Fastest way to build a DQA system with the power of LLMs.
  • In-game PPL Solution - Unity SDK for in-game advertising. Build technologies for measuring valid impressions of in-game advertisements.
  • IdolGAN - Researching and developing super resolution model for restoring K-pop girl group idols.
  • KID-F - Making high quality face image dataset of K-pop female idols.
  • Kikic - Developed a random chat app using video AI that analyzes human emotions. Android front-end, ML & back-end integration to Android.
  • Doridori Counter - Developed an automatic human head shaking detector using facial landmarks and peak detection
  • kongDak AI Development - Developed face chat which measures attractiveness score for couples
  • RubyRuby App Development - Developed baby health measurement app using rPPG & facial landmark detection
  • rPPG - Improved rPPG accuracy (SOTA at UBFC-rPPG dataset)
  • Auto-orion - Developed AutoML for TadGAN

Paper

Prizes

  • SK AI SUMMIT 2025 Claude Code Builder Hackathon, 🥇 1st Prize, SKT, Anthropic, Coxwave, 2025
  • 2024 Korea Open Source Developer Competition, 🥇 1st Prize, Ministry of Science and ICT, 2025

Contributions

Conferences/Sessions

Pinned Loading

  1. Marker-Inc-Korea/AutoRAG Marker-Inc-Korea/AutoRAG Public

    AutoRAG: An Open-Source Framework for Retrieval-Augmented Generation (RAG) Evaluation & Optimization with AutoML-Style Automation

    Python 4.7k 386

  2. NomaDamas/k-skill NomaDamas/k-skill Public

    한국인을 위한 스킬 모음집 - SRT, KTX, KBO, 카카오톡, 한글과 컴퓨터, 미세먼지, 우편번호, 블루리본 등등...

    JavaScript 1.1k 89

  3. NomaDamas/AutoRAG-Research NomaDamas/AutoRAG-Research Public

    Automate your RAG research

    Python 92 18

  4. slides-grab slides-grab Public

    Best harness + editor + linter for generating slides in Claude Code / Codex

    JavaScript 310 49

  5. NomaDamas/Noise-Cancel NomaDamas/Noise-Cancel Public

    Semantic filter for your LinkedIn Feed - now you can control what you want, not corporate.

    Python 9 3

  6. Marker-Inc-Korea/RAGchain Marker-Inc-Korea/RAGchain Public archive

    Extension of Langchain for RAG. Easy benchmarking, multiple retrievals, reranker, time-aware RAG, and so on...

    Python 284 30