Radar

Fast and extensible multi-platform HTTP/1-2-3 web server with automatic HTTPS

Local-first MCP server for supported Adobe Premiere Pro workflows. Connect Claude, Codex, or Cursor through a local CEP bridge; inspect, preview, and approve edits.

Now with support for INT8 ConvRot. The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. https://github.com/comfyanonymous/ComfyUI - Updated for Python 3.12 + torch 2.10 + cu130 (sageattention wheel fix)

Formerly KrillinAI. Open-source AI workspace for creators, powered by Codex. Create videos, images, voice, avatars, translations, and edits with Agents in one place.

Soft-fork of Bing-su/adetailer with class filtering, sequential class detection, copy/paste between tabs, per-tab settings persistence, and Forge Neo compatibility. Class-filtering pattern from wkpark/uddetailer.

Free email OSINT tool, 2500+ platforms, identity clustering, breach detection. No API keys required. pip install mailaccess

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

Ultra-lightweight text-to-speech (15M-80M params) — CPU optimized, 8 voices, ONNX-powered

Flexible Automapper for Beatsaber made for any difficulty

Contribute to hamzahelhafdaoui/abuhsituationroom4 development by creating an account on GitHub.

A live 3D intelligence console for planet Earth.

A natural language interface for computers

Self-hosted AI workspace for local-first chat, agents, tools, memory, research, documents, email, and model endpoint management.

Open source AI video engine built on Remotion. Voice cloning, AI avatars, animated captions, video editor, timeline, 100+ transitions, motion graphics, image editing, vector graphics — replaces $190+/mo in Adobe CC + Remotion Pro + SaaS. Free Synthesia/Runway/Photoshop alternative.

Describe UI and see it rendered live. Ask for changes and convert HTML to React, Svelte, Web Components, etc. Like vercel v0, but open source https://github.com/wandb/openui

An interactive resume app

Contribute to mohan696matlab/AI_CV_Customization development by creating an account on GitHub.

Contribute to RishabhP1508/DSA development by creating an account on GitHub.

[NVIDIA ONLY] Direct3D-S2 is a scalable 3D shape generation framework leveraging sparse volumetric representations for high-resolution outputs. It features Spatial Sparse Attention (SSA), a novel mechanism that accelerates Diffusion Transformer computations on sparse data, achieving up to 9.6× speedup in training. The unified Sparse VAE architecture maintains a consistent sparse volumetric format across input, latent, and output stages, significantly improving efficiency and stability.

Pinokio launcher for Higgs Audio v3 TTS with Gradio UI, SGLang-Omni backend, and automatic model download.