Ranger - a synergistic optimizer using RAdam (Rectified Adam), Gradient Centralization and LookAhead in one codebase
Repository Index
111,820 visible repositories in the index
2,161–2,184 of 3,355 · Most stars
High-fidelity performance metrics for generative models in PyTorch
AssetFurnace: the most complete open-source image-to-3D pipeline (Oct 2026). Prompt or picture → textured, rigged, animated game character, locally on Apple Silicon or NVIDIA. Pixal3D, TRELLIS.2, Hunyuan3D, SF3D, auto-rig and 21 moves. For indie game devs and 3D artists. Free, Apache-2.0.
- 3d-generation
- 3d-models
- apple-silicon
- blender
Automated Deep Learning without ANY human intervention. 1'st Solution for AutoDL challenge@NeurIPS.
One stop shop for running AI/ML on AWS.
ChainerRL is a deep reinforcement learning library built on top of Chainer.
Portfolio optimization with deep learning.
- deep-learning
- portfolio-optimization
- finance
- machine-learning
A modern open-source online judge and contest platform system.
- python
- dmoj
- dmoj-judge
- programming-contests
Implementation of CoCa, Contrastive Captioners are Image-Text Foundation Models, in Pytorch
- artificial-intelligence
- attention-mechanism
- contrastive-learning
- deep-learning
JittorGeometric is a Jittor-based graph machine learning library.
- graph
- jittor
- python
[ICCV 2019] "DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better" by Orest Kupyn, Tetiana Martyniuk, Junru Wu, Zhangyang Wang
- deblurgan
- generative-adversarial-network
- pytorch
- deep-learning
KErnel OPerationS, on CPUs and GPUs, with autodiff and without memory overflows
🌊HMTL: Hierarchical Multi-Task Learning - A State-of-the-Art neural network model for several NLP tasks based on PyTorch and AllenNLP
- natural-language-processing
- multi-task-learning
- nlp
- pytorch
A Quirky Assortment of CuTe Kernels
Python Fast Dataflow programming framework for Data pipeline work( Web Crawler,Machine Learning,Quantitative Trading.etc)
Variational autoencoder implemented in tensorflow and pytorch (including inverse autoregressive flow)
- vae
- machine-learning
- tensorflow
- variational-autoencoder
Time-series machine learning at scale. Built with Polars for embarrassingly parallel feature extraction and forecasts on panel data.
- forecasting
- machine-learning
- python
- time-series
Your iPhone helps your Mac run a 27B model: faster prompt reading and more context over a USB-C cable
Computational framework for reinforcement learning in traffic control
- reinforcement-learning
- traffic-control
- benchmark
- autonomous
🤖 A comprehensive task management system specifically designed for AI assistants. Supports project management, task tracking, team collaboration, and seamless AI integration through MCP (Model Context Protocol). Built with modern tech stack including React, Flask, and Docker. Try it now at https://todo4ai.org/
- ai-coding-tools
- cursor
- kiro
- todo4ai
icalendar parser library for Python
- hacktoberfest
- alarm
- event
- generator
My first Python repo with codes in Machine Learning, NLP and Deep Learning with Keras and Theano
- anomaly-detection
- deep-learning
- autoencoder
- keras
CUGA is an open-source generalist agent harness for the enterprise, supporting complex task execution on web and APIs, OpenAPI/MCP integrations, composable architecture, reasoning modes, and policy-aware features.
- computer-use
- enterprise
- generalist-agent
- mcp
Eliot: the logging system that tells you *why* it happened
- python
- logging
- logging-library
- tracing