MiniMind is an open-source project designed to lower the barrier to learning large language models, allowing users to train a tiny model of about 64M parameters from scratch at a very low cost (approx. 3 RMB) and in a short time (approx. 2 hours).
Open source. Open possibilities.
Discover quality open-source projects, submit projects anonymously, and claim and edit your own project.
A little curiosity. A world of open source.
THE FIRST COLLECTIONReinforcement learning library for operational decisions—pricing, inventory, energy, queues, supply chains. 31 algorithms with typed interfaces, classical baselines, and reproducible benchmarks.
Open-source prompt library for AI chat models, with web directory, CSV/MD data exports, self-hosting, interactive book, kids game, CLI, Claude Code plugin, and MCP server.
Flowise is a visual tool for building AI agents, allowing users to design and deploy agentic workflows through a graphical interface.
Eclipse Deeplearning4J (DL4J) is a JVM-based deep learning ecosystem supporting Java, Scala, Kotlin, and more. It includes model import from Keras, TensorFlow, ONNX; ND4J for linear algebra; SameDiff for automatic differentiation; DataVec for ETL; and runs on CPU/GPU across Windows, Linux, macOS.
Gestune is a touch-free system volume controller that uses hand gestures to adjust audio levels without a keyboard or mouse.
Invoke is a professional creative engine for AI-generated visual media, featuring an industry-leading web UI, Unified Canvas, node-based workflows, and support for models like Stable Diffusion, Flux, and more.
OpenCosmos is an open-source creative platform and design system ecosystem built on human-centered principles. It includes a portfolio site, community platform, AI-powered investment app, and a personal OS concept, all unified by the OpenCosmos/UI component library.
Spring AI is a Spring-native application framework for AI engineering, offering portable, strongly-typed APIs that connect enterprise data and APIs with major AI model providers and vector stores.
Official code repository for 'Build a Large Language Model (From Scratch)': step-by-step PyTorch implementation of GPT-like models, covering pretraining and finetuning with notebooks and exercises.
FiftyOne is an open-source tool for building high-quality datasets and computer vision models. It enables users to visualize, label, evaluate, and curate visual AI data.
Community-maintained tracker for worldwide computer science conference deadlines, ranked by CCF/CORE/TH-CPL. Offers a website, tabular portal, WeChat applet, plus Python CLI, iCal, Raycast, SwiftBar, Chrome and TUI extensions.
OpenHands Agent Canvas is a self-hosted developer control center for managing coding agents and automations across local, remote, and cloud backends.
A curated directory of generative AI applications, mapping the landscape of available AI tools across various domains and use cases.
Strix is an open-source AI-powered penetration testing tool that uses autonomous agents to identify, validate, and fix application vulnerabilities through real proof-of-concept exploits.
WarriorJS is an open‑source programming game where you write JavaScript or TypeScript to guide a warrior through puzzle‑filled towers, battling enemies and solving logic challenges. It teaches coding while playing.
Repomix packs an entire repository into a single AI-friendly file (XML, Markdown, JSON, or plain text) for feeding codebases into LLMs like Claude, ChatGPT, and Gemini. It offers token counting, security checks, code compression, and remote repository support.
AirSim is Microsoft's open-source simulator for drones and cars, built as an Unreal Engine plugin with an experimental Unity release. It supports software- and hardware-in-the-loop simulation with PX4 and ArduPilot, and exposes cross-language APIs for collecting images and controlling vehicles for AI research.
Real-time face swap and one-click video deepfake tool using a single source image. Features live webcam mode, face mapping for multiple subjects, mouth masking, and video processing, with support for CUDA, CoreML, DirectML, and OpenVINO acceleration.
SupaNexus is an open AI gateway that unifies access to multiple LLM providers via one API, simplifying development with OpenAI-compatible interfaces and centralized model management.