Skip to content
View IvenKooLab's full-sized avatar
  • Shenzhen, China

Block or report IvenKooLab

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

Featured in

minimax-h3-turing comfy-agent loci-dsh

What I'm working on

  • Agent & RAG: shipped a function-calling tool loop (queue / gallery / logs / launcher) in comfy-agent and loci — a queryable second brain (hybrid retrieval · MCP server)

Some things I've built

  • loci — A queryable second brain over scattered notes and docs — hybrid retrieval, cross-session memory, section-level citations, MCP server · pip install loci-rag
  • loci-dsh — Your loci second brain as a sidebar plugin in the DeepSeek Harness (dsh) web UI
  • minimax-h3-turing — Field-tested handbook and compat workflows for running MiniMax H3 on a 2080Ti 22G (Turing sm_75)
  • comfy-agent — Local-first visual studio for ComfyUI: pure-stdlib Python + vanilla JS, zero dependencies, ships as a single 10 MB exe
  • desktop-pet — 3D chibi desktop pet, with a Studio that turns AI character sheets into new pets
Snake animation eating my contribution graph

Pinned Loading

  1. 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 98 1

  2. loci-dsh loci-dsh Public

    🧠 loci second brain as a DeepSeek Harness (dsh) web plugin — search / ask / remember your local knowledge base from the sidebar

    TypeScript

  3. comfy-agent comfy-agent Public

    Local-first desktop studio for ComfyUI, built for AI short-drama production - zero-dependency 10MB exe: creation, gallery, 600+ templates, model hub, character assets (LoRA binding), episodic pipel…

    Python 26 2

  4. minimax-h3-turing minimax-h3-turing Public

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

    Python 11 1