An open-source, self-hosted personal AI note tool prioritizing privacy, built using TypeScript .

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

leaked prompts of GPTs

"Your Fully-Automated Personal AI Assistant"

Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"

Self-Adapting Language Models

Implementation of FuseMoE for FlexiModal Fusion, NeurIPS'24

Learning Deep Representations of Data Distributions

SAM-Med3D: An Efficient 3D Model for Promptable Volumetric Medical Image Segmentation

[MICCAI 2023] MedNeXt is a fully ConvNeXt architecture for 3D medical image segmentation.

Many studies have shown that the performance on deep learning is significantly affected by volume of training data. The MedicalNet project provides a series of 3D-ResNet pre-trained models and rela…

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

[ICLR 2025 Spotlight] Official implementation of "Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts"

🏅 Collection of Kaggle Solutions and Ideas 🏅

[MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.

Data descriptor and sample notebooks for the Emory Breast Imaging Dataset (EMBED) hosted on the AWS Open Data Program

A curated collection of fun and creative examples generated with Nano Banana🍌, Gemini-2.5-flash-image based model. We also release Nano-consistent-150K openly to support the community's development…

AI-powered tool that transforms STEM concepts into narrated educational animations using Manim, LLMs, and multimodal AI

A browser automation framework and ecosystem.

An LLM agent that conducts deep research (local and web) on any given topic and generates a long report with citations.

Crawlee—A web scraping and browser automation library for Python to build reliable crawlers. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Wo…

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

Faster Whisper transcription with CTranslate2

Learn to build your Second Brain AI assistant with LLMs, agents, RAG, fine-tuning, LLMOps and AI systems techniques.