Wanted

Ideogram 4: Open image model at the forefront of design

World's first open-source, agentic video production system. 11 pipelines, 49 tools, 400+ agent skills. Turn your AI coding assistant into a full video production studio.

Magenta RealTime 2: An Open-Weights Live Music Model

A local, open-source alternative to NotebookLM. Chat with your documents using any LLM.

A fully self-contained, offline AI image generation studio for Windows. Runs Stable Diffusion (Safetensors/GGUF) locally with zero manual setup. Auto-configures CUDA for Nvidia GPUs and Vulkan for AMD/Intel Arc cards. Zero system-wide dependencies required.

Repository for the CVPR 2026 paper MeshFlow Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformer by Weiyu Li, Antoine Toisoul, Tom Monnier, Roman Shapovalov, Rakesh Ranjan, Ping Tan and Andrea Vedaldi.

Ideogrammar — Ideogram 4 Prompt Editor A single-file, no-build web app for composing structured Ideogram 4 prompts.

Local web UI for the DiffusionGemma diffusion LLM — watch answers crystallize out of noise

open-source healthcare ai

Run GGUF models easily with a KoboldAI UI. One File. Zero Install.

A natural language interface for computers

Contribute to TomClive/SeeDance2Stitcher development by creating an account on GitHub.

Control panel for VLLM, Sglang, llama.cpp, exllamav3

A generative speech model for daily dialogue.

Zonos2 is a leading open-weight text-to-speech MoE.

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

AI Browser

OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched

2.24x decode TPS increase On Qwen 3.6 27B @ temp 0.6 | Native MTP Speculative Decoding On Apple Silicon With No External Drafter.

リアルタイムボイスチェンジャー Realtime Voice Changer