This is your work, valued
Research Associate in Machine Learning, interested in the intersection of multi-modal learning and meta-learning.
HowToTrainYourMAMLPytorch. The original code for the paper "How to train your MAML" along with a replication of the original "Model Agnostic Meta Learning" (MAML) paper in Pytorch.
★ 826DAGAN. DAGAN: Data Augmentation Generative Adversarial Networks
★ 419MatchingNetworks. An attempt at replicating the Matching Networks for One Shot Learning in Tensorflow - Paper URL: https://arxiv.org/pdf/1606.04080.pdf
★ 334Learning_to_Learn_via_Self-Critique. The original code for the paper "Learning to Learn via Self-Critique".
★ 48minimal-ml-template. A very minimal ml project template that uses HF transformers and wandb to train a simple NN and evaluate it, in a stateless manner compatible with Spot instances kubernetes workflows
★ 45FewShotContinualLearning. The original code for the paper "Benchmarks for Continual Few-Shot Learning".
★ 36kubejobs. Python
★ 32DeepClassificationBot. A deep learning powered bot capable of classifying images into user-specified categories
★ 26FewShotContinualLearningDataProvider. The original code for the data providers and the datasets of the paper "Defining Benchmarks for Continual Few-Shot Learning".
★ 16TemplateProjectCDTGPUCluster. Python
★ 10infk8s-tutorial. Dockerfile
★ 8AwesomeGPTSystemPrompts.
★ 4GATE. Python
★ 3TALI. Python
★ 3lerobot-instruction-synthesis. Python
★ 3TPUSanityCheck. Python
★ 3WhisperSpeechToTextApp. A minimal python app that allows easy and quick speech to text for lecture-note taking
★ 2nanoGPT. An adapted version of the simplest, fastest repository for training/finetuning medium-sized GPTs.
★ 2CAPIT. Jupyter Notebook
★ 2mlpractical-2019. Machine Learning Practical course repository
★ 1learn2learn. A PyTorch Library for Meta-learning Research
★ 1mlpractical-2. Machine Learning Practical Course Code Repository
★ 1mlpractical-1. Machine Learning Practical course repository
★ 1LearningToReadCharacterByCharacter. Python
★ 1hephie. Hephie -- from Hephaestus -- is an AI assistant designed by a software engineer for other software engineers
★ 1workmux. git worktrees + tmux windows for zero-friction parallel dev
★ 2kespigue. Topic in, cited literature review out — drives literature search from the disagreements and gaps it finds, every citation and quote mechanically verified. pip-installable, OpenRouter-backed.
★ 2prompt_injection. Fine-tune axiotic/ogma-base on neuralchemy/Prompt-injection-dataset
★ 3symphonia. HTML
★ 2hermes-agent. The agent that grows with you
★ 223kclaude-code-telegram. A powerful Telegram bot that provides remote access to Claude Code, enabling developers to interact with their projects from anywhere with full AI assistance and session persistence.
★ 2.7kclaw-orchestrator. Run Claude Code, Codex, Gemini, Cursor Agent and custom coding CLIs as one unified runtime for claw-style agent systems. Runs standalone, with first-class OpenClaw plugin support.
★ 542moltis. A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and MCP tools. Secure by design, runs on your hardware.
★ 2.8kmemUBot. The Enterprise-Ready OpenClaw. Your Proactive AI Assistant That Remembers Everything
★ 451nanobot. Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps
★ 46kironclaw. IronClaw is an Agent OS focused on privacy, security and extensibility
★ 13kopenclaw. Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
★ 385kvideo2x. A machine learning-based video super resolution and frame interpolation framework. Est. Hack the Valley II, 2018.
★ 21kawesome-openclaw-skills. The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞
★ 52kmemU. Personal memory across agents
★ 14kclaude-mem. Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
★ 89kopencode. The open source coding agent.
★ 191kmodel2vec. Fast State-of-the-Art Static Embeddings
★ 2.2kno-as-a-service. No-as-a-Service (NaaS) is a simple API that returns a random rejection reason. Use it when you need a realistic excuse, a fun “no,” or want to simulate being turned down in style.
★ 7.8kZ-Image. Python
★ 12kGoogle-Research-MCP. MCP Server built for use with Claude Code, Claude Desktop, VS Code, Cline - enable google search and ability to follow links and research websites
★ 250llm-council. LLM Council works together to answer your hardest questions
★ 23krl-swarm. A fully open source framework for creating RL training swarms over the internet.
★ 1.7kmodelcontextprotocol. The official MCP server implementation for the Perplexity API Platform
★ 2.4kRWKV-LM. RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
★ 15kchatterbox. SoTA open-source TTS
★ 26kUSearch. Fast Open-Source Search & Clustering engine × for Vectors & Arbitrary Objects × in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram 🔍
★ 4.2kReview-Gate. Review-Gate V2 is a powerful rule for the Cursor IDE that helps you get up to 5x more value from your monthly requests. It creates an interactive loop where the AI waits for your follow-up commands—via text, voice, or image upload—allowing you to perform deep, iterative work all within a single request.
★ 1.5kopen-webui. User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
★ 147kSpeech. A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
★ 18kSO-ARM100. Standard Open Arm 100
★ 6.9kmaml_tryout. [WIP] Implementation of MAML (https://doi.org/10.48550/arXiv.1703.03400) in a flexible and reusable manner, as well as variations of it.
★ 1exo. Run frontier AI locally.
★ 47kllama_cloud_services. Knowledge Agents and Management in the Cloud
★ 4.3kllama3.1-405b-ChatGPT-4x-comparison. Jupyter Notebook
★ 1miniforge. A conda-forge distribution.
★ 10kqlora. QLoRA: Efficient Finetuning of Quantized LLMs
★ 11kasuswrt-merlin.ng. Extends the support of Merlin firmware to more ASUS routers
★ 2.3kmanim. Animation engine for explanatory math videos
★ 89kLLM101n. LLM101n: Let's build a Storyteller
★ 38kMMLU-Pro. The code and data for "MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark" [NeurIPS 2024]
★ 416aim. Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.
★ 6.2kTransformerEngine. A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory utilization in both training and inference.
★ 3.5kparsyncfp. follow-on to parsync (parallel rsync) with better startup perf
★ 177openmediavault. openmediavault is the next generation network attached storage (NAS) solution based on Debian Linux. Thanks to the modular design of the framework it can be enhanced via plugins. openmediavault is primarily designed to be used in home environments or small home offices.
★ 6.9kuptime-kuma. A fancy self-hosted monitoring tool
★ 90kawesome-selfhosted. A list of Free Software network services and web applications which can be hosted on your own servers
★ 309kuv. An extremely fast Python package and project manager, written in Rust.
★ 88kFFCV-SSL. FFCV-SSL Fast Forward Computer Vision for Self-Supervised Learning.
★ 217vllm. A high-throughput and memory-efficient inference and serving engine for LLMs
★ 88kRecoverPy. Interactively find and recover deleted or :point_right: overwritten :point_left: files from your terminal
★ 1.8kBend. A massively parallel, high-level programming language
★ 20kmodular. The Modular Platform (includes MAX & Mojo)
★ 27kpython-latex-highlighting. LaTeX style for Python highlighting
★ 473PyLaTeX. A Python library for creating LaTeX files
★ 2.4ksecret-llama. Fully private LLM chatbot that runs entirely with a browser with no server needed. Supports Mistral and LLama 3.
★ 2.7kpokerogue. A browser based Pokémon fangame heavily inspired by the roguelite genre.
★ 5.8knanoGPT. The simplest, fastest repository for training/finetuning medium-sized GPTs.
★ 62kfairscale. PyTorch extensions for high performance and large scale training.
★ 3.4kllama-cookbook. Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services
★ 19kllama3. The official Meta Llama 3 GitHub site
★ 29kexllama. A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.
★ 2.9kllama.cpp. LLM inference in C/C++
★ 122kchatgpt-web. ChatGPT web interface using the OpenAI API
★ 2kevery-chatgpt-gui. Every front-end GUI client for ChatGPT, Claude, and other LLMs
★ 4kipydatagrid. Fast Datagrid widget for the Jupyter Notebook and JupyterLab
★ 641v-d4rl. Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations
★ 115typingmind. The most advanced Web UI for AI chat
★ 954cityscapesScripts. README and scripts for the Cityscapes Dataset
★ 2.3kpyo3. Rust bindings for the Python interpreter
★ 16kivy. Convert Machine Learning Code Between Frameworks
★ 14ktorchgeo. TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data
★ 4.1ksignal-export. Export your Signal chats to markdown files with attachments
★ 766Minari. A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities
★ 1.3kD4RL. A collection of reference environments for offline reinforcement learning
★ 1.7kkubernetes. Production-Grade Container Scheduling and Management
★ 124kblue. The slightly less uncompromising Python code formatter.
★ 410awesome-tips.
★ 4.7kcluster-scripts. A collection of useful scripts, templates, and examples for clusters using SLURM https://slurm.schedmd.com/
★ 115archive-old-cli-mentat. Python
★ 2.5ktabby. Self-hosted AI coding assistant
★ 34kGPTCodeAssist. GPTCodeAssist: Harness the power of OpenAI's GPT for your codebase. Generate code, detect errors, and receive refactoring suggestions. Boost your development workflow and accelerate project progress.
★ 17mpv. 🎥 Command line media player
★ 36kiina. The modern video player for macOS.
★ 46kCoreMLPlayer. Try CoreML models on multiple images and videos easily and quickly
★ 167my-spaces. Run hugging face spaces locally with one command!
★ 60pixi. Powerful system-level package manager for Linux, macOS and Windows written in Rust – building on top of the Conda ecosystem.
★ 7.5kijepa. Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive architecture."
★ 3.5kllama2.c. Inference Llama 2 in one file of pure C
★ 20ksherlock. Hunt down social media accounts by username across social networks
★ 87kawesome-mac. This project is dedicated to collecting high-quality macOS software and organizing them systematically by different categories for easy search and use.
★ 109kawesome-mac. Mac awesome MacOS Apps
★ 104ControlNet. Let us control diffusion models!
★ 34kopen_clip. An open source implementation of CLIP.
★ 14kgpt-4-chat-ui. This project is a simple React-based chat interface that uses Next.js and communicates with OpenAI's GPT-4 (or GPT-3.5-turbo) language model to generate responses.
★ 110mmsegmentation. OpenMMLab Semantic Segmentation Toolbox and Benchmark.
★ 9.9klens. Lens - The way the world runs Kubernetes
★ 23kSegmenTron. Support PointRend, Fast_SCNN, HRNet, Deeplabv3_plus(xception, resnet, mobilenet), ContextNet, FPENet, DABNet, EdaNet, ENet, Espnetv2, RefineNet, UNet, DANet, HRNet, DFANet, HardNet, LedNet, OCNet, EncNet, DuNet, CGNet, CCNet, BiSeNet, PSPNet, ICNet, FCN, deeplab)
★ 723pytorch-segmentation. :art: Semantic segmentation models, datasets and losses implemented in PyTorch.
★ 1.8kOneFormer. [CVPR 2023] OneFormer: One Transformer to Rule Universal Image Segmentation
★ 1.7kSegVit. Official Pytorch Implementation of SegViT: Semantic Segmentation with Plain Vision Transformers
★ 263safetensors. Simple, safe way to store and distribute tensors
★ 3.8kgit-crypt. Transparent file encryption in git
★ 9.8kblackbox. Safely store secrets in Git/Mercurial/Subversion
★ 6.8kmae. PyTorch implementation of MAE https//arxiv.org/abs/2111.06377
★ 8.4kLAVIS. LAVIS - A One-stop Library for Language-Vision Intelligence
★ 11kViLT. Code for the ICML 2021 (long talk) paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"
★ 1.5kcommitgpt. Automatically generate commit messages using ChatGPT
★ 1.6ksignalbackup-tools. Tool to work with Signal Backup files.
★ 1.4kchatgpt-clone. ChatGPT interface with better UI
★ 3.5ktutorials. MONAI Tutorials
★ 2.5ksegmentation_models.pytorch. Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
★ 12kViT-Adapter. [ICLR 2023 Spotlight] Vision Transformer Adapter for Dense Predictions
★ 1.5kevals. Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
★ 19kAutoGPT. AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
★ 186kSimpleParsing. Simple, Elegant, Typed Argument Parsing with argparse
★ 543StableLM. StableLM: Stability AI Language Models
★ 16ktmate. Instant Terminal Sharing
★ 6.1kjax. Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
★ 36kJARVIS. JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
★ 25kRocket.Chat. The Secure CommsOS™ for mission-critical operations
★ 46kcommunity-skeleton. UVdesk Open Source Community Helpdesk is a comprehensive ticketing support system designed for everyone, offering robust features to streamline customer support and collaboration.
★ 19kattentions. PyTorch implementation of some attentions for Deep Learning Researchers.
★ 548simple-hierarchical-transformer. Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT
★ 228tox. Command line driven CI frontend and development task automation tool.
★ 3.9ktmux. 🧛🏻♂️ Dark theme for tmux
★ 852PyAV. Pythonic bindings for FFmpeg's libraries.
★ 3.2kVideoProcessingFramework. Set of Python bindings to C++ libraries which provides full HW acceleration for video decoding, encoding and GPU-accelerated color space and pixel format conversions
★ 1.4kdecord. An efficient video loader for deep learning with smart shuffling that's super easy to digest
★ 2.5kkube-fledged. A kubernetes operator for creating and managing a cache of container images directly on the cluster worker nodes, so application pods start almost instantly
★ 1.4kema-pytorch. A simple way to keep track of an Exponential Moving Average (EMA) version of your Pytorch model
★ 658open-source-mac-os-apps. 🚀 Awesome list of open source applications for macOS. https://t.me/s/opensourcemacosapps
★ 50kgitify. Git notifications on your menu bar. Available on macOS, Windows & Linux.
★ 5.3kpython-fire. Python Fire is a library for automatically generating command line interfaces (CLIs) from absolutely any Python object.
★ 28kkubectl-plugins. My own plugins for kubectl
★ 371whisper_mic. Project that allows one to use a microphone with OpenAI whisper.
★ 788torchtyping. Type annotations and dynamic checking for a tensor's shape, dtype, names, etc.
★ 1.5kdocker-examples. There are many like it, but this one is mine.
★ 81datashim. A kubernetes based framework for hassle free handling of datasets
★ 530mistral. Mistral: A strong, northwesterly wind: Framework for transparent and accessible large-scale language model training, built with Hugging Face 🤗 Transformers.
★ 581pytorch-template. PyTorch deep learning projects made easy.
★ 5.1kkubernetes-yaml-templates. Kubernetes Yaml Templates
★ 663generate-k8s-yaml. TypeScript
★ 10gradio. Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!
★ 43khaikus-for-codespaces. EJS
★ 2.8kvscode-remote-try-python. Python sample project for trying out Dev Containers
★ 933vscode-dev-containers. NOTE: Most of the contents of this repository have been migrated to the new devcontainers GitHub org (https://github.com/devcontainers). See https://github.com/devcontainers/template-starter and https://github.com/devcontainers/feature-starter for information on creating your own!
★ 4.7kBIG-bench. Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models
★ 3.2koutline-wiki-docker-compose. Installation and docker compose to self host outline wiki: https://www.getoutline.com/
★ 315outline. The fastest knowledge base for growing teams. Beautiful, realtime collaborative, feature packed, and markdown compatible.
★ 40kproject-wiki-template.
★ 91AI-Render. Stable Diffusion in Blender
★ 1.2kthefuck. Magnificent app which corrects your previous console command.
★ 98kninja. a small build system with a focus on speed
★ 13ksampleproject. A sample project that exists for PyPUG's "Tutorial on Packaging and Distributing Projects"
★ 5.2kDreambooth-Stable-Diffusion. Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion
★ 7.7kdiffusers. 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
★ 34kwaifu-diffusion. stable diffusion finetuned on weeb stuff
★ 1.9kkubeflow-distribution. Blueprints for Deploying Kubeflow on Google Cloud Platform and Anthos
★ 81docker-fish-shell. 🐳🐟🐚Docker image for the Friendly Interactive Shell, aka fish
★ 17hydra-zen. Create powerful Hydra applications without the yaml files and boilerplate code.
★ 470iris. Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.
★ 898machine-learning-docker-template. Jupyter Notebook
★ 2cresset. Template repository to build PyTorch projects from source on any version of PyTorch/CUDA/cuDNN.
★ 718deep-learning-containers. One stop shop for running AI/ML on AWS.
★ 1.2kawesome-bashrc. 🚀 Collection of bash snippets/aliases that will save your time on the terminal
★ 216mlresearch.github.io. Machine Learning Research Homepage
★ 48stylegan2-pytorch. Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement
★ 3.8kawesome-pretrained-stylegan. A collection of pre-trained StyleGAN models to download
★ 333DeepFaceLab. DeepFaceLab is the leading software for creating deepfakes.
★ 19kGANimation. GANimation: Anatomically-aware Facial Animation from a Single Image (ECCV'18 Oral) [PyTorch]
★ 2kawesome-face. An awesome face technology repository.
★ 1.3kkitty-themes. A collection of themes for kitty terminal 😻
★ 3.2kDART_retinal_fractal_dimension. Code for "robust and efficient computation of retinal fractal dimension through deep approximation"
★ 10jobs. Open job listings and company information for Draft.dev
★ 83obs-pulseaudio-app-capture. OBS plugin to capture application audio from PulseAudio
★ 60instaloader. Download pictures (or videos) along with their captions and other metadata from Instagram.
★ 13kvideo-diffusion-pytorch. Implementation of Video Diffusion Models, Jonathan Ho's new paper extending DDPMs to Video Generation - in Pytorch
★ 1.4kmastodon. Your self-hosted, globally interconnected microblogging community
★ 50kflickr_scraper. Python Flickr image scraper for building keyword-based computer vision datasets with pagination and deduplication.
★ 290wezterm. A GPU-accelerated cross-platform terminal emulator and multiplexer written by @wez and implemented in Rust
★ 28knos. Module to Automatically maximize the utilization of GPU resources in a Kubernetes cluster through real-time dynamic partitioning and elastic quotas - Effortless optimization at its finest!
★ 683lightning-maml. MAML Implementation using Pytorch-lightning
★ 24Adversarial-Continual-Learning. Implementation for the paper "Adversarial Continual Learning" in PyTorch.
★ 255quickdraw-dataset. Documentation on how to access and use the Quick, Draw! Dataset.
★ 6.8klearn2learn. A PyTorch Library for Meta-learning Research
★ 2.9kfgvcx_fungi_comp. FGVCx Fungi Classfiication competition details
★ 53ml_collections. ML Collections is a library of Python Collections designed for ML use cases.
★ 1kfiddle. Python
★ 386pydantic. Data validation using Python type hints
★ 28kStyleAlign. HTML
★ 152DALL-E. PyTorch package for the discrete VAE used for DALL·E.
★ 11kpytorch-CycleGAN-and-pix2pix. Image-to-Image Translation in PyTorch
★ 25komegaconf. Flexible Python configuration system. The last one you will ever need.
★ 2.4kcoqpit. Simple but maybe too simple config management through python data classes. We use it for machine learning.
★ 107jsonlint. JSON command-line parsing and checking for Mac OS X
★ 17datasets. 🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools
★ 22ktask_adaptation. Python
★ 352wandb. The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.
★ 11ksustainbench. Python
★ 122