Skip to content
View SuperJufufu's full-sized avatar
  • Joined Nov 1, 2026

Block or report SuperJufufu

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. 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
SuperJufufu/README.md

Hi, I'm SuperJufufu 👋

High-school student. I build local AI infrastructure and the automation around it.

Most of what's here started as "I want my machine to do this by itself" and ended as a working system: local model routing, end-to-end generation pipelines that audit their own output, and a lot of Windows plumbing that nobody else wanted to touch.

Main direction

Local-first AI stack — agent orchestration, model routing, and generation pipelines that check their own work.

What I've built

Repo What it is
screendim C# daemon: turn the physical backlight off via DDC/CI while screen capture & OCR keep working
local-ensemble-shim OpenAI-compatible shim that ensembles two local models (multi-view + judge) with guards for real local-model failure modes
windows-pitfalls Battle-tested PowerShell/VBS fixes: icon cache, autostart chaos, silent launchers, OEM codepage traps
condense Compress long docs with a local LLM before feeding a cloud model — fewer input tokens, same answers

How I work

measure it → break it → find the root cause → leave a handoff doc the next agent can use

  • I orchestrate AI agents to ship systems — my unit of work is a system, not a function
  • Everything gets a rollback path: backup → patch → verify → document what will silently break next time
  • I care about the boring numbers: tokens, VRAM, watts, startup time, how many seconds before it degrades

Stack — PowerShell · Python · Node.js · C# · Ollama · llama.cpp · ComfyUI · SillyTavern

Currently: high school + too many background processes.

Popular repositories Loading

  1. screendim screendim Public

    Turn off the monitor backlight (DDC/CI) while screen capture, recording and OCR keep working — Windows daemon in C#. No black frames.

    C# 1

  2. condense condense Public

    Cut cloud LLM input tokens: pre-summarize long documents and logs with a local model to 1-3% of their size. Single-file Python, stdlib only.

    Python

  3. windows-pitfalls windows-pitfalls Public

    Battle-tested fixes for badly documented Windows pain: blank shortcut icons, 40+ autostart entries, OEM codepage, VBS launchers, self-recreating services.

    PowerShell

  4. local-ensemble-shim local-ensemble-shim Public

    OpenAI-compatible shim that ensembles two local models (draft + judge) and guards real local-LLM failure modes: degeneration, tool-call repair, context overflow.

    Python

  5. SuperJufufu SuperJufufu Public

    SuperJufufu profile

  6. sillytavern-dsh-pack sillytavern-dsh-pack Public

    SillyTavern DSH extension pack: 13 extensions, optional AGPL patches, one-click Windows installer

    JavaScript