Trending Projects

Complete LLM training implementation: pretraining, SFT, DPO, and RLHF from scratch in Python

Accelerates production deployment of AI agents with scale, reliability, and security via the Amazon Bedrock Agentcore.

GigaBrain-0 is a powerful AI model that enables vision-language-action capabilities for vibe coders.

An open-source tutorial that helps developers deploy large language models (LLMs) like Ollama on CPU for production use.

A modular simulation framework and benchmark for robot learning using reinforcement learning and physics simulation.

A high-performance 3D rendering library for ray tracing and hybrid rasterization of Gaussian particles.

A Python library for state-of-the-art generative image models, focused on AI and machine learning tools for vibe coders.

Provides TypeScript access to Anthropic's safety-first language model APIs for building AI-powered applications.

A Python-based desktop AI assistant that integrates with various LLMs and AI tools for coding, task automation, and more.

A curated list of papers on Agential Language Models and Reinforcement Learning for AI developers.

A Python library with nodes related to video workflows for ComfyUI, a Stable Diffusion UI.

A powerful agent framework for building intelligent personal assistants with multi-agent collaboration and tool integration.

A curated list of 100+ resources for building and deploying generative AI, focused on helping you become a Generative AI Data Scientist.

A curated list of best AI resources for developers, including tutorials, libraries, and tools.

A collection of machine learning projects for developers to learn and apply various ML techniques.

A CLI text-to-speech tool using the Kokoro model, supporting multiple languages and input formats.

A Python library for inspecting and understanding neural network models using PatchCore.

KAI Scheduler is an open source Kubernetes-native scheduler for AI workloads at large scale.

A 3D reconstruction and simulation framework for urban scenes, focused on omnidirectional imagery.

PyTorch Lightning simplifies deep learning training and deployment at scale.

Official FLUX.1 inference repo for image generation & editing

SHAP explains ML model outputs using Shapley values for interpretability.

PyTorch implementation of CycleGAN and pix2pix for image-to-image translation

Interactive machine learning algorithms in Python with Jupyter demos

Recommenders is a project for prototyping and operationalizing recommendation systems with Jupyter notebooks and best practices.

Rasa is an open-source framework for building conversational AI agents with NLU and dialogue management.

A framework for evaluating large language models (LLMs) and an open-source registry of benchmarks.

LLM agents built for real-world use, designed for control and deployed in minutes.

A set of Jupyter Notebooks that combine Grounding DINO, Segment Anything, and Stable Diffusion for automatic detection, segmentation, and generation of anything in images.

Sealos is an AI-native Cloud Operating System that unifies the entire application lifecycle for building and scaling modern AI applications.

Toolkit for linearizing PDFs to create LLM datasets/training

A deep learning model that converts images of mathematical equations into LaTeX code.

RWKV is an RNN-based language model with high performance, fast training, and flexible transformer-like architecture.

A free MLOps course that covers machine learning model deployment and monitoring

An open-source implementation of the LoRA (Low-Rank Adaptation) technique for fine-tuning large language models.

A collection of current AI agents used for developer discovery and collaboration.

A web UI for the Stable Diffusion AI text-to-image generation model, enabling developers to create and customize AI-powered image generation.

A PyTorch implementation of the U-Net for image semantic segmentation with high quality images.

Fast and accurate machine learning framework that can build models in just 3 lines of Python code.

An open-source, large language model-based multimodal dialogue system that achieves near-GPT-4o performance.

A robust, efficient, and low-latency speech-to-text library with advanced voice activity detection and wake word activation.

NVIDIA CUDA samples that demonstrate features of the CUDA Toolkit for GPU-accelerated development.

TypeChat is a TypeScript library that makes it easy to build natural language interfaces using types.

ORB-SLAM3 is an open-source library for visual, visual-inertial, and multi-map SLAM (Simultaneous Localization and Mapping).

Text-audio foundation model from Boson AI for vibe coders building AI-powered applications.

An open-source, low-latency AI avatar platform for building interactive digital humans.

An open-source face recognition system with a rich set of computer vision features and APIs.

This repository contains an efficient implementation of a vision encoding model for vision-language models.

A flexible workflow orchestration platform that seamlessly integrates data, ML, and analytics stacks.

An open-source LLM framework to build AI-powered tools and applications.