Trending Projects

The ultimate toolkit for finetuning diffusion models, a key component of AI-powered coding tools.

Voice conversion framework with web UI for training and real-time voice models

AI-powered resume tailoring with local model support

An implementation of the YOLOv9 object detection model, a state-of-the-art computer vision AI.

A powerful Bayesian modeling and probabilistic programming library for Python developers.

MLflow is an open-source platform for building, tracking, and deploying AI/ML models with end-to-end observability and evaluation tools.

Ray is a unified framework for scaling AI and Python applications with distributed computing and ML libraries.

DeepSeek-OCR for visual-text compression and OCR tasks

A fully automated AI-powered short video engine for generating videos from text, images, and audio.

Fast and flexible image augmentation library for computer vision and machine learning projects.

Optimized attention mechanism for deep learning

Kodezi Chronos is a state-of-the-art debugging-first language model for code analysis and bug fixing.

A collection of AI-powered projects, including machine learning, deep learning, and generative AI, for developers.

Unofficial Python API for interacting with Google's NotebookLM, a large language model for code generation.

Hindsight is an agent-based memory system that aims to work like human memory, built for AI developers.

VybeGuide.ai discovery platform for vibe coders

A Python library for using and fine-tuning over 900 large language models and multimodal models for various AI tasks.

An open-source browser extension that provides immersive translation capabilities for developers working with AI tools.

A Python framework for building high-performance multi-agent systems with AI tools and agents.

Automate your mobile devices with natural language commands using an LLM-agnostic mobile agent.

WhisperX for fast ASR with word-level timestamps and diarization

A PyTorch-based reference implementation and models for the DINOv3 self-supervised vision transformer.

Barebones NumPy ML implementations for learning

A local-first chat analysis tool that uses SQL and AI agents to relive and explore social memories

This open-source project generates infinite-length, high-quality videos using diffusion transformers and error recycling.

Python robotics algorithms and textbook for developers.

An open-source AI avatar toolkit for offline video generation and digital human cloning.

A powerful tool for easy and efficient video subtitling using large language models.

A powerful JavaScript tool for creating datasets for fine-tuning large language models (LLMs) and retrieval-augmented generation (RAG).

Kimi K2 is a large language model series developed by Moonshot AI team for AI-powered coding tools and applications.

AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.

Nugget is a Python library that unlocks the full potential of your device with AI-powered tools and features.

An open-source machine learning engineering reference with resources for training, deploying, and scaling AI models.

Cross-platform ML framework for real-time media processing

A natural language interface for computers

Production-ready templates to quickly ship AI agents to Google Cloud with built-in CI/CD, evaluation, and observability.

Dolphin is a document image parsing library that uses heterogeneous anchor prompting for OCR and layout analysis.

AI-powered desktop client for multiple LLMs with local storage and cross-platform support

Deep learning paper implementations with side-by-side notes and explanations

Supercharge your large language models (LLMs) with the fastest key-value cache layer for lightning-fast inference.

Offline speech-to-text engine for real-time on-device use

A PoC for a technique to recover plaintext from pixelized screenshots.

Fastest LLM gateway with adaptive load balancer, cluster mode, guardrails, and 1000+ models support.

中文ChatGPT提示词指南，涵盖多种使用场景

A Python library that uses OpenAI's Whisper to enable offline audio transcription and translation.

An AI-powered framework for Java developers to build intelligent, context-aware applications.

Demystify AI agents by building them yourself with no black boxes, real understanding of function calling, memory, and ReAct patterns.

Comprehensive LLM engineering and application resources with training, inference, compression, and deployment guides

A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.

Qwen3 is Alibaba Cloud's large language model series with enhanced reasoning and coding capabilities.