HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation

Valdi is a cross-platform UI framework that delivers native performance without sacrificing developer velocity.

A Gtk/Qt front-end to tesseract-ocr.

Krea Realtime 14B. An open-source realtime AI video model.

Contexts Optical Compression

An Open Source implementation of Notebook LM with more flexibility and features

tl/dw (Too Long, Didn't Watch): Your Personal Research Multi-Tool - a naive attempt at 'A Young Lady's Illustrated Primer' (Open Source NotebookLM)

the IDE for research, built from the ground up with AI integrations

Local-first, open-source AI assistant for your data. Unify tasks, notes, docs, photos, and bookmarks. Private, self-hosted, and extensible via APIs.

Read-through cache for object storage

A beautiful local-first coding agent running in your terminal - built by the community for the community ⚒

Lemonade helps users run local LLMs with the highest performance by configuring state-of-the-art inference engines for their NPUs and GPUs. Join our discord: https://discord.gg/5xXzkMu8Zk

🔥🔥 Open-sourced unified customization model

Wan: Open and Advanced Large-Scale Video Generative Models

A powerful GUI app and Toolkit for Claude Code - Create custom agents, manage interactive Claude Code sessions, run secure background agents, and more.

Open-source platform to build and deploy AI agent workflows.

Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors

The glamourous AI coding agent for your favourite terminal 💘

Validate and Run GitHub Actions locally.

Lock, Stock, and Two Smoking MicroVMs. Create and manage the lifecycle of MicroVMs backed by containerd.

🔥 Clone and recreate any website as a modern React app in seconds

Your Creative Copilot for Video Editing

ScreenCoder — Turn any UI screenshot into clean, editable HTML/CSS with full control. Fast, accurate, and easy to customize.

Repair invalid JSON documents

wacat - Challenge Your Web App with Cat Chaos and AI-Driven Testing!

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

Quick Connections for ComfyUI & litegraph

An open-source authorization as a service inspired by Google Zanzibar, designed to build and manage fine-grained and scalable authorization systems for any application.

A tool for creating and running Linux containers using lightweight virtual machines on a Mac. It is written in Swift, and optimized for Apple silicon.

Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)