Mr. For Example

Blender-For-UnrealEngine-Addons. I have created this addons for export asset from Blender to Unreal Engine

XNALara-io-Tools. Blender Import/Export add-on for XPS Models and Poses [Blender 4.x port]

three.js. JavaScript 3D Library.

Babylon.js. Babylon.js is a powerful, beautiful, simple, and open game and rendering engine packed into a friendly JavaScript framework.

llm-viz. 3D Visualization of an GPT-style LLM

transformers.js. State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

onnx. Open standard for machine learning interoperability

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

mlflow. The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data.

captum. Model interpretability and understanding for PyTorch

shap. A game theoretic approach to explain the output of any machine learning model.

opik. Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

torchlens. Capture every activation and gradient of any PyTorch model — forward and backward — with automatic graph visualization, rich metadata, and live interventions. Works on any architecture, including dynamic and recurrent ones.

tensorspace. Neural network 3D visualization framework, build interactive and intuitive model in browsers, support pre-trained deep learning models from TensorFlow, Keras, TensorFlow.js

rust-gpu. 🐉 Making Rust a first-class language and ecosystem for GPU shaders 🚧

nanite-at-home. Nanite made from scratch in Rust as my master thesis

nanite-webgpu. UE5's Nanite implementation using WebGPU. Includes the meshlet LOD hierarchy, software rasterizer and billboard impostors. Culling on both per-instance and per-meshlet basis.

OLMo. Modeling, training, eval, and inference code for OLMo

hidden-networks. Python

netron. Visualizer for neural network, deep learning and machine learning models

torchvista. Interactive Pytorch forward pass visualization in notebooks

torchview. torchview: visualize pytorch models

pytorchviz. A small package to create visualizations of PyTorch execution graphs

MotionStream. MotionStream: Real-Time Video Generation with Interactive Motion Controls

memobase. User Profile-Based Long-Term Memory for AI Chatbot Applications.

airi. 💖🧸 Self hosted, you-owned Grok Companion, a container of souls of waifu, cyber livings to bring them into our worlds, wishing to achieve Neuro-sama's altitude. Capable of realtime voice chat, Minecraft, Factorio playing. Web / macOS / Windows supported.

kokoro_training. Training code for kokoro tts model

StyleTTS2. StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models

godot. Godot Engine – Multi-platform 2D and 3D game engine

Prompt-Baking. Jupyter Notebook

SLM-Bench. Python

SparCL. SparCL: Sparse Continual Learning on the Edge @ NeurIPS 22

LoRI. [COLM 2025] LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation

chatterbox. SoTA open-source TTS

dia. A TTS model capable of generating ultra-realistic dialogue in one pass.

index-tts. An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

Orpheus-TTS. Towards Human-Sounding Speech

EmotiVoice. EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine

StableAvatar. We present StableAvatar, the first end-to-end video diffusion transformer, which synthesizes infinite-length high-quality audio-driven avatar videos without any post-processing, conditioned on a reference image and audio.

MultiTalk. [NeurIPS 2025] Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation

InfiniteTalk. ​​Unlimited-length talking video generation​​ that supports image-to-video and video-to-video generation

ton. Main TON monorepo

nobodywho. NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.

LakonLab. Official implementation of AsymFlow, pi-Flow, GMFlow

flash-attention. Fast and memory-efficient exact attention

BitNet. Official inference framework for 1-bit LLMs

MobileLLM-R1. MobileLLM-R1

MobileLLM. MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.

ai-toolkit. The ultimate training toolkit for finetuning diffusion models

LightX2V-Qwen-Image-Lightning. Qwen-Image-Lightning: Speed up Qwen-Image model with distillation

streaming-vlm. StreamingVLM: Real-Time Understanding for Infinite Video Streams

DC-VideoGen. DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder

EqM. Python

LiftFeat. Code for "LiftFeat: 3D Geometry-Aware Local Feature Matching", ICRA2025

efficientvit. Efficient vision foundation models for high-resolution generation and perception.

RIPE. [ICCV 2025] Keypoint detection and description learned from image pairs only - no depth, no pose, no artificial augmentation required.

SSDD. Official implementation for SSDD Single-Step Diffusion Decoder for Efficient Image Tokenization.

LightX2V. Lightweight Image Video Action Generation Inference Framework

nunchaku. [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

cwm. Research code artifacts for Code World Model (CWM) including inference tools, reproducibility, and documentation.

fuwari. ✨A static blog template built with Astro.

Random_Pruning. [ICLR 2022] The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training by Shiwei Liu, Tianlong Chen, Xiaohan Chen, Li Shen, Decebal Constantin Mocanu, Zhangyang Wang, Mykola Pechenizkiy

DA-2. Official implementation of "DA²: Depth Anything in Any Direction"

DC-Gen. DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space

hard-ash. Python

ShinkaEvolve. ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program Evolution 🧬

FlyModel. Unofficial Python implementation of "Algorithmic insights on continual learning from fruit flies"

SDMContinualLearner. Jupyter Notebook

Orientation_Matters. Official repository for the paper "Orientation Matters: Making 3D Generative Models Orientation-Aligned" (NeurIPS 2025)

SceneMover. Project of Siggraph Asia 2020 paper: Scene Mover: Automatic Move Planning for Scene Arrangement by Deep Reinforcement Learning

satsom. Saturation Self-Organizing Map

SageAttention. [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

UniRig. [SIGGRAPH 2025] One Model to Rig Them All: Diverse Skeleton Rigging with UniRig

Elevate3D. Python

HunyuanWorld-1.0. Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels with Hunyuan3D World Model

PartPacker. Efficient Part-level 3D Object Generation via Dual Volume Packing

MindJourney. [NeurIPS 2025] Source codes for the paper "MindJourney: Test-Time Scaling with World Models for Spatial Reasoning"

PartCrafter. [NeurIPS 2025] PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers

Bella. Bella is best

HiDream-I1. Python

cupy. NumPy & SciPy for GPU

anima-x. Official Implementation of [AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models]

brian2. Brian is a free, open source simulator for spiking neural networks.

dendrify. Introducing dendrites to spiking neural networks. Designed for the Brian 2 simulator.

transformations. Homogeneous transformation matrices and quaternions.

Hunyuan3D-2.1. From Images to High-Fidelity 3D Assets with Production-Ready PBR Material

stochastic_transition. Python

ComfyUI_InstantID. Python

algovivo. An energy-based formulation for soft-bodied virtual creatures

morphology-adaptive. Morphology-adaptive muscle-driven locomotion via attention mechanisms

x-flux-comfyui. Python

ComfyUI-IPAdapter-Flux. Python

Anymate. Python

worker-comfyui. ComfyUI as a serverless API on Runpod

docling. Get your documents ready for gen AI

crawl4ai. 🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN

firecrawl. The API to search, scrape, and interact with the web at scale. 🔥

reader. Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/

deep-research. Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.

MV-Painter. Python

triton-windows. Fork of the Triton language and compiler for Windows support and easy installation

Direct3D-S2. [NeurIPS 2025] Direct3D‑S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention

ComfyUI-MVAdapter. Custom nodes for using MV-Adapter in ComfyUI.

continuous-thought-machines. Continuous Thought Machines, because thought takes time and reasoning is a process.

Step1X-3D. Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets

liquid-s4. Liquid Structural State-Space Models

PyNN. A Python package for simulator-independent specification of neuronal network models.

bindsnet. Simulation of spiking neural networks (SNNs) using PyTorch.

nest-simulator. The NEST simulator

Absolute-Zero-Reasoner. Official Repository of Absolute Zero Reasoner

local-deep-research. ~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.

python-markdownify. Convert HTML to Markdown

DeepGit. Deep research agent to help you find the best GitHub repositories 🕵️!

deep-searcher. Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.

deep-research-web-ui. (Supports DeepSeek R1) An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models.

node-DeepResearch. Keep searching, reading webpages, reasoning until it finds the answer (or exceeding the token budget)

deep-research. An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the simplest implementation of a deep research agent - e.g. an agent that can refine its research direction overtime and deep dive into a topic.

local-deep-researcher. Fully local web research and report writing assistant

open_deep_research. Python

EdgeRunner. [ICLR 2025] EdgeRunner: Auto-regressive Auto-encoder for Efficient Mesh Generation

Graphics-LPIPS. Python

NR-3DQA. Point cloud version for "No-Reference Quality Assessment for 3D Colored Point Cloud and Mesh models".

TripoSG. TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models

sleep-time-compute. accompanying material for sleep-time compute paper

liquid_time_constant_networks. Code Repository for Liquid Time-Constant Networks (LTCs)

neo4j. Graphs for Everyone

knowledge-graph-of-thoughts. Official Implementation of "Affordable AI Assistants with Knowledge Graph of Thoughts"

SAMPart3D. SAMPart3D: Segment Any Part in 3D Objects

HoloPart. HoloPart: Generative 3D Part Amodal Segmentation

Second-Me. Train your AI self, amplify you, bridge the world

AI-Scientist-ICLR2025-Workshop-Experiment. Python

AI-Scientist-v2. The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

d3. Bring data to life with SVG, Canvas and HTML. :bar_chart::chart_with_upwards_trend::tada:

d3-force. Force-directed graph layout using velocity Verlet integration.

TriplaneTurbo. [CVPR2025] Progressive Rendering Distillation: Adapting Stable Diffusion for Instant Text-to-Mesh Generation without 3D Data

PBR3DGen. [AAAI 2026] PBR3DGen: A VLM-guided mesh generation with High-Quality PBR texture

zstd. Zstandard - Fast real-time compression algorithm

TexGaussian. [CVPR 2025] TexGaussian: Generating High-quality PBR Material via Octree-based 3D Gaussian Splatting

TripoSF. SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling

Orient-Anything. Orient Anything, ICML 2025

Stable3DGen. A Modular Framework for 3D Generation and Beyond [WIP]

TreeMeshGPT. [CVPR 2025] TreeMeshGPT: Artistic Mesh Generation with Autoregressive Tree Sequencing

py7zr. 7zip in python3 with ZStandard, PPMd, LZMA2, LZMA1, Delta, BCJ, BZip2, and Deflate compressions, and AES encryption.

DeepMesh. [ICCV 2025] Official code of DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning

FlashVDM. Unleashing Vecset Diffusion Model for Fast Shape Generation / within 1 Second (ICCV'25 Highlight)

panda3d. Powerful, mature open-source cross-platform game engine for Python and C++, developed by Disney and CMU

dm_nevis. NEVIS'22: Benchmarking the next generation of never-ending learners

MIDI-3D. [CVPR 2025] MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation

DiscoPOP. Code for Discovering Preference Optimization Algorithms with and for Large Language Models

GPTSwarm. 🐝 The First Self-Improving agents with RL / Prompting Optimization

llm_debate. Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"

ADAS. [ICLR 2025] Automated Design of Agentic Systems

Wan2.1. Wan: Open and Advanced Large-Scale Video Generative Models

AgentLaboratory. Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas

MeshLib. Mesh processing library

pytorch_volumetric. Volumetric structures such as voxels and SDFs implemented in pytorch

recurrent-pretraining. Pretraining and inference code for a large-scale depth-recurrent language model

fpsample. Python efficient farthest point sampling (FPS) library. Compatible with numpy.

pyvista. 3D visualization and mesh analysis for science and engineering

meshio. :spider_web: input/output for many mesh formats

POP. Official implementation of the ICCV 2021 paper: "The Power of Points for Modeling Humans in Clothing".

3DShape2VecSet. Python

Dora. [CVPR 2025] Official repository for "Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoders"

posthog. :hedgehog: PostHog is the leading platform for building self-driving products. Our developer tools – AI observability, analytics, session replay, flags, experiments, error tracking, logs, and more – capture all the context agents need to diagnose problems, uncover opportunities, and ship fixes. Steer it all from Slack, web, desktop, or the MCP.

MCMat. Code of MCMat: Multiview-Consistent and Physically Accurate PBR Material Generation;

ITEM3D. Our paper "Directional Texture Editing for 3D Models" has been accepted by Computer Graphics Forum (CGF), 2024

Janus. Janus-Series: Unified Multimodal Understanding and Generation Models

MeshAnythingV2. [ICCV 2025] From anything to mesh like human artists. Official impl. of "MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization"

leapfusion-hunyuan-image2video. A novel approach to hunyuan image-to-video sampling

CaPa. Official Repository of **CaPa**: Carve-n-Paint Synthesis for Efficient 4K Textured Mesh Generation

pybind11. Seamless operability between C++11 and Python

gpytoolbox. A collection of utility functions to prototype geometry processing research in python

Hunyuan3D-2. High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

large_concept_model. Large Concept Models: Language modeling in a sentence representation space

Slow_Thinking_with_LLMs. A series of technical report on Slow Thinking with LLM

Qwen3. Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

openr. OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models

LlamaV-o1. [ACL 2025 🔥] Rethinking Step-by-step Visual Reasoning in LLMs

MiniMax-01. The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attention

LlamaFactory. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

SkyThought. Sky-T1: Train your own O1 preview model within $450

loss-of-plasticity. Demonstrations of Loss of Plasticity and Implementation of Continual Backpropagation

metamotivo. The first behavioral foundation model to control a virtual physics-based humanoid agent for a wide range of whole-body tasks.

BrainSimIII. C#

semanticscholar. Unofficial Python client library for Semantic Scholar APIs.

stable-point-aware-3d. SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images

streaming-drl. Deep reinforcement learning without experience replay, target networks, or batch updates.

scholarly. Retrieve author and publication information from Google Scholar in a friendly, Pythonic way without having to worry about CAPTCHAs!

arxiv.py. Python wrapper for the arXiv API

VAR. [NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!

LatentSync. Taming Stable Diffusion for Lip Sync!

react-use-websocket. React Hook for WebSocket communication

Awesome-Multimodal-Next-Token-Prediction. [Survey] Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey

sqlitebrowser. Official home of the DB Browser for SQLite (DB4S) project. Previously known as "SQLite Database Browser" and "Database Browser for SQLite". Website at:

LayoutVLM. Official code for "LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models" (CVPR 2025)

awesome-vlm-architectures. Famous Vision Language Models and Their Architectures

IDArb. Official repo for "IDArb: Intrinsic Decomposition for arbitrary number of input views and illuminations"

Comfy3D-WinPortable. 🧊ComfyUI-3D-Pack pre-built for Windows. | Comfy3D 整合包

Neural-LightRig. [CVPR2025] Neural LightRig: Unlocking Accurate Object Normal and Material Estimation with Multi-Light Diffusion

ComfyUI-IF_Trellis. ComfyUI TRELLIS is a large 3D asset generation in various formats, such as Radiance Fields, 3D Gaussians, and meshes. The cornerstone of TRELLIS is a unified Structured LATent (SLAT) representation that allows decoding to different output formats and Rectified Flow Transformers tailored for SLAT as the powerful backbones.