The agent that grows with you

Any model. Any hardware. Zero compromise. Built with @ziglang / @openxla / MLIR / @bazelbuild

OHIF zero-footprint DICOM viewer and oncology specific Lesion Tracker, plus shared extension packages

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

An AI Hedge Fund Team

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

Web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.

Unsupervised Learning for Image Registration

Anserini is a Lucene toolkit for reproducible information retrieval research

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

"RAG-Anything: All-in-One RAG Framework"

Turn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.

Natural language interface to NCI Imaging Data Commons

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

Advanced algorithmic trading framework for MetaTrader 5 featuring multi-strategy portfolio optimization, intelligent risk management, and quantitative execution. Built in MQL5 for professional syst…

This repository contains implementations and illustrative code to accompany DeepMind publications

The official gpt4free repository | various collection of powerful language models | opus 4.6 gpt 5.3 kimi 2.5 deepseek v3.2 gemini 3

Graph Neural Network Library for PyTorch

Transformers for Clinical NLP

TIGRE: Tomographic Iterative GPU-based Reconstruction Toolbox

Making large AI models cheaper, faster and more accessible

Kronos: A Foundation Model for the Language of Financial Markets

A one-size-fits-all solution to run nnU-Net models. Supports TotalSegmentator models.

MLX inference backend for nnU-Net on Apple Silicon

Tool for robust segmentation of >100 important anatomical structures in CT and MR images

📚 Playground and cheatsheet for learning Python. Collection of Python scripts that are split by topics and contain code examples with explanations.

Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.

tiktoken is a fast BPE tokeniser for use with OpenAI's models.