Skip to content
View IvenKooLab's full-sized avatar
1 follower · 1 following
  • Shenzhen, China

Block or report IvenKooLab

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

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

Report abuse
IvenKooLab/README.md

Hi, I'm Iven Koo

Full-stack developer. Running a local AI video production pipeline (2080Ti + MiniMax H3), with a habit of turning every pitfall I hit into documentation.

What I'm working on

  • Building applications in the Agent & RAG space — just shipped a function-calling tool loop (queue / gallery / logs / launcher) in comfy-agent; RAG is next

Some things I've built

  • comfy-agent — Local-first visual studio for ComfyUI: pure-stdlib Python + vanilla JS, zero dependencies, ships as a single 10 MB exe
  • minimax-h3-turing — Field-tested handbook and compat workflows for running MiniMax H3 on a 2080Ti 22G (Turing sm_75)

Popular repositories Loading

  1. comfy-agent comfy-agent Public

    Local-first visual studio for ComfyUI — pure-stdlib Python + vanilla JS, zero dependencies, single 10 MB exe

    JavaScript 2

  2. minimax-h3-turing minimax-h3-turing Public

    MiniMax H3 video generation on 2080Ti 22G (Turing sm_75) - field-tested handbook, workflows & FAQ

    Python 2 1

  3. violin-schedule violin-schedule Public

    A cute timetable PWA for violin tutors — or any one-on-one teacher. Pure frontend, data stays yours

    JavaScript 1

  4. IvenKooLab IvenKooLab Public

    Full-stack developer × AI — building real things: desktop apps, video pipelines, and the docs along the way

  5. loci loci Public

    A queryable second brain over your scattered notes and docs - hybrid retrieval (vector + BM25), section-level citations, and an MCP server so AI agents can use it. ~300 lines, no LangChain.

    Python

  6. awesome-minimax-h3-integration awesome-minimax-h3-integration Public

    Forked from MiniMax-AI/awesome-minimax-h3-integration