Skip to content
View oney-erge's full-sized avatar
8 followers · 6 following

Achievements

Achievement: QuickdrawAchievement: Pair Extraordinairex2Achievement: Pull Sharkx3Achievement: YOLO

Achievements

Achievement: QuickdrawAchievement: Pair Extraordinairex2Achievement: Pull Sharkx3Achievement: YOLO

Block or report oney-erge

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
oney-erge/README.md

Oney Erge

I build practical tools for local AI and experiments where agents meet physics. My focus is making research easy to run, inspect, and reproduce. PhD in Dynamic Systems and Control, UT Austin.

  • Afterimage: run supported BF16 language models beyond GPU memory and reproduce inference measurements.
  • LocalDeploy: choose, run, and measure local models on your own hardware.
  • YBM: carry out supervised computer tasks with approvals and receipts.
  • AgentGymnasium: evaluate AI agents on visual physics challenges.
  • Creature Lab: design and diagnose simulated robot bodies and controllers.
  • SegCraft: train and run semantic segmentation on images and video.

Portfolio, writing, publications, and patents · LinkedIn · Google Scholar

Outside of AI: I grew up on 90s and early 2000s PC games and still go back to them. Some things just hold up.

Pinned Loading

  1. YBM YBM Public

    A local AI agent for real computer work, with planning, approvals, execution, verification, and audit trails.

    Python

  2. Afterimage Afterimage Public

    A research toolbox for running and studying LLMs on constrained hardware, with memory, placement, inference, and benchmarking methods.

    Python 1

  3. LocalDeploy LocalDeploy Public

    Find, deploy, manage, and benchmark local AI models for your hardware across Ollama, llama.cpp, and compatible runtimes.

    Python

  4. SegCraft-Semantic-Segmentation SegCraft-Semantic-Segmentation Public

    A config-first toolkit for semantic segmentation training, evaluation, and image/video inference.

    Python 2 2

  5. AgentGymnasium AgentGymnasium Public

    A visual physics environment where LLM agents build, simulate, evaluate, and iteratively improve physical designs.

    Python

  6. Creature-Lab Creature-Lab Public

    A local workbench for robot morphology experiments: design bodies, run physics, diagnose behavior, and improve designs through reproducible trials.

    Python