z

ponytail. Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

harness-1. 🚀 Ultra Recipe for Training Long-Horizon Search Agents - matching frontier AI's search capability with a 20B model + stateful harness

rlm. General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.

HOPEJr. HOPEJr_open-source_DIY_Humanoid_Robot_with_dexterous_hands

ouroboros. Agent OS: Stop prompting. Start specifying.

camofox-browser. Stealth headless browser for AI agents — bypass Cloudflare, bot detection, and anti-scraping. Drop-in Puppeteer/Playwright replacement.

endless-terminals. Python

loophole. Python

llama.cpp. LLM inference in C/C++

le-wm. Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

autonovel. An autonomous novel writing pipeline, by Hermes Agent

stop-slop. A skill file for removing AI tells from prose

tlaplus. TLC is a model checker for specifications written in TLA+. The TLA+Toolbox is an IDE for TLA+.

pinchtab. High-performance browser automation bridge and multi-instance orchestrator with advanced stealth injection and real-time dashboard.

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

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

tenacitOS. OpenClaw Mission Control Dashboard

desloppify. Agent harness to make your slop code well-engineered and beautiful.

craftium. A framework for creating rich, 3D, Minecraft-like single and multi-agent environments for AI research. (Accepted at ICML 2025).

claude-subconscious. Give Claude Code a subconscious

hermes-agent. The agent that grows with you

picoclaw. Tiny, Fast, and Deployable anywhere — automate the mundane, unleash your creativity

openclaw. Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

openevolve. Open-source implementation of AlphaEvolve

music-audio-representations. Results and Models for Learning Audio Representations of Music Content

node-autoit-koffi. This Node.js module provides support for all AutoIt functions, allowing users to automate Windows GUI tasks seamlessly.

mcp-windows-desktop-automation. A Model Context Protocol (MCP) server for Windows desktop automation using AutoIt.

copyparty. Portable file server with accelerated resumable uploads, dedup, WebDAV, SFTP, FTP, TFTP, zeroconf, media indexer, thumbnails++ all in one file

neko. A self hosted virtual browser that runs in docker and uses WebRTC.

vaultwarden. Unofficial Bitwarden compatible server written in Rust, formerly known as bitwarden_rs

atropos. Atropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse environments

kontext-lab. HTML

lerobotdepot. LeRobotDepot is a community-driven repository listing open-source hardware, components, and 3D-printable projects compatible with the LeRobot library. It helps users easily discover, build, and contribute to affordable, accessible robotics solutions powered by state-of-the-art AI.

CM6_COBOT_ROBOT. Files and intro page for first version of CM6 COBOT robotic arm

setta. Streamline Python coding, configuration, UI creation, and onboarding.

sunnypilot. sunnypilot is an open source driver assistance system. sunnypilot offers the user a unique driving experience for over 350 supported car makes and models with modified behaviors of driving assist engagements. sunnypilot complies with the safety policy from comma.ai's openpilot as accurately as possible.

opendbc. a Python API for your car

comfyui_dygen. Dy Mokomi Custom Nodes for ComfyUI

Core-R-Theta-4-Axis-Printer. 4 Axis 3D Printer

Radial_Non_Planar_Slicer. G-code

fsdp_optimizers. supporting pytorch FSDP for optimizers

SPiT. A Spitting Image: Modular Superpixel Tokenization in Vision Transformers

tt-metal. :metal: TT-NN operator library, and TT-Metalium low level kernel programming model.

Muon. Muon is an optimizer for hidden layers in neural networks

layered_vectorization. JavaScript

scrap. 📸 Screen capture made easy!

diamond. DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.

DynamicVectorQuantization. Official Pytorch Implementation of Our CVPR2023 Paper: "Towards Accurate Image Coding: Improved Autoregressive Image Generation with Dynamic Vector Quantization"

tt-buda. Tenstorrent TT-BUDA Repository

pyglove. Manipulating Python Programs

flux. Official inference repo for FLUX.1 models

sigma-gpt. σ-GPT: A New Approach to Autoregressive Models

sparsify. Sparsify transformers with SAEs and transcoders

haliax. Named Tensors for Legible Deep Learning in JAX

optax. Optax is a gradient processing and optimization library for JAX.

orbax. Orbax provides common checkpointing and persistence utilities for JAX users

levanter. Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax

equinox. Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

flax. Flax is a neural network library for JAX that is designed for flexibility.

llm.c. LLM training in simple, raw C/CUDA

Megatron-LM. Ongoing research training transformer models at scale

HVM2. A massively parallel, optimal functional runtime in Rust

mmdit. Implementation of a single layer of the MMDiT, proposed in Stable Diffusion 3, in Pytorch

FourierKAN. Python

pykan. Kolmogorov Arnold Networks

diffusion-kto. The official implementation of Diffusion-KTO: Aligning Diffusion Models by Optimizing Human Utility

torchtitan. A PyTorch native platform for training generative AI models

pyo3. Rust bindings for the Python interpreter

Score-Entropy-Discrete-Diffusion. [ICML 2024 Best Paper] Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution (https://arxiv.org/abs/2310.16834)

Betterfox. Firefox user.js for optimal privacy and security. Your favorite browser, but better.

p5.brush. Unlock custom brushes, natural fill effects and intuitive hatching in p5.js

gptq. Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

backtesting.py. 🔎 📈 🐍 💰 Backtest trading strategies in Python.

Weylus. Use your tablet as graphic tablet/touch screen on your computer.

typst. A markup-based typesetting system that is powerful and easy to learn.

PocketKitchen-UI. Pocket Kitchen | Node.js & Express web app and MongoDB data pipleline for presenting actionable food waste prevention insights

hccl_demo. C++

candle. Minimalist ML framework for Rust

Hotshot-XL. ✨ Hotshot-XL: State-of-the-art AI text-to-GIF model trained to work alongside Stable Diffusion XL

ProPainter. [ICCV 2023] ProPainter: Improving Propagation and Transformer for Video Inpainting

bark. 🔊 Text-Prompted Generative Audio Model

generative_agents. Generative Agents: Interactive Simulacra of Human Behavior

minSDXL. Huggingface-compatible SDXL Unet implementation that is readily hackable

novelai-aspect-ratio-bucketing. Implementation of aspect ratio bucketing for training generative image models as described in: https://blog.novelai.net/novelai-improvements-on-stable-diffusion-e10d38db82ac

OnnxStream. Lightweight inference library for ONNX files, written in C++. It can run Stable Diffusion XL 1.0 on a RPI Zero 2 (or in 298MB of RAM) but also Mistral 7B on desktops and servers. ARM, x86, WASM, RISC-V supported. Accelerated by XNNPACK. Python, C# and JS(WASM) bindings available.

blibla-comfyui-extensions. Extensions for ComfyUI

LLaVAR. Code/Data for the paper: "LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding"

MeZO. [NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333

uss. This is the PyTorch implementation of the Universal Source Separation with Weakly labelled Data.

prolificdreamer. ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation (NeurIPS 2023 Spotlight)

audio-diffusion. Python

StableLM. StableLM: Stability AI Language Models

All-In-One-Deflicker. [CVPR2023] Blind Video Deflickering by Neural Filtering with a Flawed Atlas

composer. Official implementation of "Composer: Creative and Controllable Image Synthesis with Composable Conditions"

ComfyUI. The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

ChatGPT. Reverse engineered ChatGPT API

ControlNet. Let us control diffusion models!

xg2xg. by ex-googlers, for ex-googlers - a lookup table of similar tech & services

ui. A set of beautifully-designed, accessible components and a code distribution platform. Works with your favorite frameworks. Open Source. Open Code.

JWildfire. JWildfire - powerful, flexible and user-friendly fractal flame editor

audiolm-pytorch. Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch

audio-dataset. Audio Dataset for training CLAP and other models

RDM-Region-Aware-Diffusion-Model. Python

dygen. Swift

sd-leap-booster. Fast finetuning using a booster model that puts the initial state to a local minimum

awesome-design-patterns. A curated list of software and architecture related design patterns.

diffvg. Differentiable Vector Graphics Rasterization

Dreambooth-Stable-Diffusion. Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) by way of Textual Inversion (https://arxiv.org/abs/2208.01618) for Stable Diffusion (https://arxiv.org/abs/2112.10752). Tweaks focused on training faces, objects, and styles.

stable-dreamfusion. Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.

submitit. Python 3.8+ toolbox for submitting jobs to Slurm

AITemplate. AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

Dreambooth-Stable-Diffusion. Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion

textual_inversion. Jupyter Notebook

stable-diffusion. Jupyter Notebook

DiSS. Adaptively-Realistic Image Generation from Stroke and Sketch with Diffusion Model (WACV 2023)

stability-sdk. SDK for interacting with stability.ai APIs (e.g. stable diffusion inference)

krita. Krita is a free and open source cross-platform application that offers an end-to-end solution for creating digital art files from scratch built on the KDE and Qt frameworks.

stable-diffusion. A latent text-to-image diffusion model

toma. Helps you write algorithms in PyTorch that adapt to the available (CUDA) memory

GODEL. Large-scale pretrained models for goal-directed dialog

dalle2-laion. Pretrained Dalle2 from laion

brain-tokyo-workshop. 🧠🗼

ema-pytorch. A simple way to keep track of an Exponential Moving Average (EMA) version of your Pytorch model

diffusers. 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

pytorch. Tensors and Dynamic neural networks in Python with strong GPU acceleration

imagen-pytorch. Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch

instant-ngp. Instant neural graphics primitives: lightning fast NeRF and more

accelerate. 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

checkout. Action for checking out a repo

setup-python. Set up your GitHub Actions workflow with a specific version of Python

gh-action-pypi-publish. The blessed :octocat: GitHub Action, for publishing your :package: distribution files to PyPI, the tokenless way: https://github.com/marketplace/actions/pypi-publish

aesthetic-predictor. A linear estimator on top of clip to predict the aesthetic quality of pictures

DALLE-pytorch. Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch

lightweight-gan. Implementation of 'lightweight' GAN, proposed in ICLR 2021, in Pytorch. High resolution image generations that can be trained within a day or two

Thin-Plate-Spline-Motion-Model. [CVPR 2022] Thin-Plate Spline Motion Model for Image Animation.

CLIP. CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

dalle-mini. DALL·E Mini - Generate images from a text prompt

tortoise-tts. A multi-voice TTS system trained with an emphasis on quality

embedding-dataset-reordering. Reorders the embeddings generated by CLIP to be in line with the webdatasets generated by img2dataset.

python-template. Simple python template

Awesome-Diffusion-Models. A collection of resources and papers on Diffusion Models

img2dataset. Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

clip_benchmark. clip retrieval benchmark

STEGO. Unsupervised Semantic Segmentation by Distilling Feature Correspondences

flamingo-pytorch. Implementation of 🦩 Flamingo, state-of-the-art few-shot visual question answering attention net out of Deepmind, in Pytorch

medical. This repository will be a summary and outlook on all our open, medical, AI advancements.

clip-image-search. Fine-tuning OpenAI CLIP Model for Image Search on medical images

glid-3-xl. 1.4B latent diffusion model fine tuning

NeuralNeighborStyleTransfer. Optimization based style transfer

django-tailwind. Django + Tailwind CSS = 💚

black. The uncompromising Python code formatter

webdataset. A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.

embedding-reader. Efficiently read embedding in streaming from any filesystem

contrastive-unpaired-translation. Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV 2020, in PyTorch)

DALLE2-pytorch. Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch

Detic. Code release for "Detecting Twenty-thousand Classes using Image-level Supervision".

pipdeptree. A command line utility to display dependency tree of the installed Python packages

latent-diffusion. High-Resolution Image Synthesis with Latent Diffusion Models

aiaiart. Course content and resources for the AIAIART course.

Tensor-Puzzles. Solve puzzles. Improve your pytorch.

eg3d. Python

magma. MAGMA - a GPT-style multimodal model that can understand any combination of images and language. NOTE: The freely available model from this repo is only a demo. For the latest multimodal and multilingual models from Aleph Alpha check out our website https://app.aleph-alpha.com

GAMA-GAT. Guided Adversarial Attack for Evaluating and Enhancing Adversarial Defenses, NeurIPS Spotlight 2020

ru-dolph. RUDOLPH: One Hyper-Tasking Transformer can be creative as DALL-E and GPT-3 and smart as CLIP

dl_tutor. Jupyter Notebook