Neon AI is an open-source voice application development platform that combines artificial intelligence and natural language understanding capabilities, supporting the creation of voice-interaction applications similar to smart voice assistants.

ComfyUI is a modular graphical interface tool for Stable Diffusion that uses a node-based workflow design, making it easier for users to control the image generation process in greater detail.

Qdrant Vector Database is an open-source vector database and search engine focused on efficient vector similarity retrieval. It supports the development of embedding-vector-based applications such as search, matching, and recommendations through APIs.

Open Voice OS is an open-source project for voice artificial intelligence, operating as a community-driven Linux distribution designed to enable voice AI to be deployed and customized across devices such as smart speakers, phones, and TVs.

Genmo AI is an AI-based video generation tool focused on quickly turning ideas into visually expressive content, and it also provides community-generated works for browsing and reference.

Inpainter is an AI image restoration and completion tool based on the Stable Diffusion model and the Replicate API, used to generate or fill missing areas in images, and it provides API and GitHub-related resources.

AIimages is a local AI image generation tool for Windows that lets users generate images through text prompts. It is based on Stable Diffusion, supports free unlimited creation, and allows generated images to be used for commercial purposes.

MiniGPT-4 is an open-source multimodal image-text generation model based on the Vicuna-related architecture. It can understand images and generate text content, making it suitable for research and experimental scenarios such as image description and visual question answering.

AgentGPT is a tool for creating and deploying AI agents. Users only need to set an agent name and goal, and it can automatically execute and plan around the task.

Public Prompts is an open-source image generation prompt resource library that collects a variety of high-quality prompts to help creators gain inspiration and use them for AI art creation.

Kiri.art is a free and open-source Stable Diffusion web frontend that provides a clean, mobile-first interface for generating AI art images, with support for various settings and sharing.

CopyFish is a free browser OCR extension that supports Chrome, Firefox, and Edge. It can recognize text from screenshots or images and convert it into editable text for easy copying, organizing, and reuse.

Pickapic is an image generation and evaluation tool for AI research. Users can generate images from text, rank and download them, and support improvements to text-to-image models through human feedback.

Markprompt is an open-source GPT prompt-building tool for Markdown documents. It supports Markdown, Markdoc, and MDX content processing, and provides component integration and analytics features to help teams build intelligent Q&A experiences based on documentation and improve documentation quality.

Genmo is an AI tool that generates videos from text. After users enter text content, they can quickly create videos with style and music options, lowering the professional skill requirements for video creation.

Harmonai is a community-driven open-source generative audio project dedicated to providing AI tools for music creation, enabling more people to participate in sound and music generation practice.

OSS Insight is a GPT-powered GitHub data exploration tool that supports generating SQL with natural language, querying real-time open-source data, and displaying results visually.

DeepLearning.AI is an online education platform founded by renowned AI expert Andrew Ng, offering high-quality machine learning and deep learning courses to help learners gradually master AI skills from beginner to advanced levels. The platform’s courses cover both theoretical knowledge and practical applications, combined with real-world cases, making it suitable for learners at different levels.

A free and open-source deep learning framework

Open-source deep learning platform

Upscayl is a beautifully designed free and open-source AI image upscaling tool that supports desktop systems including Windows, Mac, and Linux, and is used by more than one million users. With state-of-the-art artificial intelligence, Upscayl can help you convert low-resolution images into high-resolution ones.

Gemma is a family of lightweight, advanced open AI models developed by Google DeepMind and other Google teams. Built on the same technology as the Gemini models, it is designed to help developers and researchers build responsible AI applications. The Gemma model family includes models with two weight sizes: Gemma 2B and Gemma 7B, offering both pretrained and instruction-tuned versions, with support for multiple frameworks such as JAX, PyTorch, and TensorFlow for efficient operation across different devices.

AiPy is a free and open-source AI agent factory, a local version of Manus, built on large language models (LLMs) and Python capabilities. It supports local deployment to ensure data privacy and security. Through the "Python-Use" paradigm, AiPy gives AI "hands," enabling it to analyze local data, operate local applications, and execute complex tasks such as controlling phones, generating multi-voice speech, analyzing medical test reports, extracting speech from videos, and sending scheduled emails.