-
Fuzzy Bunny Labs
- Brooklyn, NY
Stars
LeHami: Symplectic Latent Dynamics for World Models
Hands-on Colab notebooks for building agents with Deep Agents and evaluating them with LangSmith
The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and build across disciplines: CAD, circuits, r…
Give AI agents ambitious work without losing the plot. nac is an open-source harness for long-running tasks, using a central orchestrator, threads, and structured episodes to stay aligned with your…
LLM-as-a-Verifier is a general-purpose framework that provides fine-grained feedback for any agent without requiring additional training. It achieves SOTA performance across coding, robotics, and m…
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
The open-source AI workbench for scientific research
Learn how a GPU works, then write CUDA code. Plain-English lessons with interactive diagrams.
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
Reflection Removal through Efficient Adaptation of Diffusion Transformers
A custom MARL (multi-agent reinforcement learning) environment where multiple agents trade against one another (self-play) in a zero-sum continuous double auction. Ray [RLlib] is used for training.
Official code repo for the O'Reilly Book - "Hands-On Large Language Models"
Kronos: A Foundation Model for the Language of Financial Markets
A high-throughput and memory-efficient inference and serving engine for LLMs
The #1 AI Harness for Building Resumes, PDFs, Cover Letters & more, locally with 100+ LLMs support.
An open-source AI agent that brings the power of Gemini directly into your terminal.
[TMLR2026] Video Prediction Transformers without Recurrence or Convolution
PyTorch code and models for VJEPA2 self-supervised learning from video.
PathOn Robotics Open Source Repo on building and controlling real robots
Grant LLM access to a Docker container for running commands
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026]
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
MindSpore + 🤗Huggingface: Run any Transformers/Diffusers model on MindSpore with seamless compatibility and acceleration.
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
A professional list of Tutorials and Surveys on DL, ML, DM, CV, NLP, Speech in top AI conferences and journals.
This repo contains the code for the paper "Intuitive physics understanding emerges fromself-supervised pretraining on natural videos"
This repo is for the Linkedin Learning course: Advanced AI: Transformers for Computer Vision