Trending Projects

A TypeScript library that allows developers to enhance the capabilities of the Claude AI language model.

ControlNet adds conditional control to diffusion models for precise image generation.

Qwen-Image is a powerful AI-powered image generation model for complex text rendering and precise image editing.

A curated catalogue of awesome agentic AI patterns for developers building with AI tools.

Industrial-strength NLP library for Python with pretrained models and fast processing

DeepSeek-OCR for visual-text compression and OCR tasks

An automated document analyzer for Paperless-ngx using various AI services to tag your documents.

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

A curated list of 100+ libraries and frameworks for AI engineers building with large language models (LLMs).

A curated list of top AI tools and frameworks for developers building with AI technologies.

Fay is an agent framework that helps connect digital humans and large language models to business systems.

Multimodal conversational video generation powered by AI, enabling new vibe-coder collaboration experiences.

An efficient zero-shot text-to-speech system with fine-grained control over the generated voice.

An open source SDK for logging, storing, querying, and visualizing multimodal and multi-rate data.

A Python-based agent that uses speech recognition and text-to-speech to enable conversational interactions via WhatsApp.

A high-performance linear algebra library for GPU-accelerated deep learning and other applications.

Open-source KVM software for developers focused on building with AI tools and technologies.

Automated decryption/decoding/cracking tool using AI and NLP

Run state-of-the-art 🤗 Transformers AI models directly in the browser, without a server.

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.

Python SDK for Anthropic's Claude AI agent, enabling developers to build AI-powered applications.

Cozeloop is an open-source platform that provides full-lifecycle management for AI agent development, debugging, and monitoring.

The LLM vulnerability scanner, a Python-based tool for identifying security vulnerabilities in large language models.

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

A Python framework for generating AI-powered PowerPoint presentations using large language models.

A highly configurable and extensible Rime input scheme for Chinese writing with AI-powered word suggestions.

Open source implementation of CLIP, a contrastive learning model for multi-modal tasks like zero-shot classification.

A Rust framework for blazingly fast inference of ML models using zero-knowledge proofs.

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

A Python-based library for solving visual understanding tasks using reinforced visual-linguistic models (VLMs).

Deploy serverless AI workflows at scale with the Julep AI agent framework built on Firebase.

Object detection toolbox for PyTorch with support for multiple tasks and state-of-the-art models.

An AI-powered OSINT tool for investigating the dark web, built using Python and LLMs.

An event-driven framework for building and orchestrating multi-agent AI systems with real-world data integration.

Simplified facial recognition API for Python and command line

OCRFlux is a powerful PDF-to-Markdown conversion toolkit with advanced layout handling, table parsing, and cross-page content merging.

HunyuanVideo is a systematic framework for large-scale video generation using diffusion models and transformers.

An open-source robotics simulation platform for developing and testing AI-driven robots in virtual environments.

A guide for preparing for technical interviews in machine learning and AI topics.

Rapid and powerful OCR toolkit for developers, supporting multiple AI frameworks like ONNX, OpenVINO, and PyTorch.

A neural network library for speaker diarization, including speech activity detection, speaker change detection, and speaker embedding.

A Go-based multi-channel AI proxy with intelligent key rotation for vibe coders using AI tools

DeepFaceLab is the leading software for creating deepfakes and other face manipulation tasks.

An open-source anomaly detection library with state-of-the-art algorithms and features like experiment management and edge inference.

A production-ready multi-agent AI framework for automating tasks and solving complex problems using LLMs.

Solutions and notes for the Machine Learning Specialization by Andrew NG on Coursera.

High-performance LLM deployment engine for cross-platform AI model execution

This is a comprehensive guide for building with the LLaMA language model, covering inference, fine-tuning, and end-to-end solutions.

Deep learning tutorial for image processing with PyTorch and TensorFlow2