Stars
Free, open-source tiling window manager for Apple Silicon Macs, with Niri-style scrolling containers and Hyprland-style Dwindle BSP.
The ultimate training toolkit for finetuning diffusion models
YuE2 music generation and an editable piano roll for ComfyUI
Record your screen, ship a demo. Free and open-source, GPU-accelerated, no watermarks, no subscriptions. Windows, macOS, Linux. Actively maintained.
Turn the user's description or uploaded reference into a finished, editable Blender card and an interactive Three.js page. Preserve the requested subject, style, typography and destination. This sk…
Neural latent upscaler for Minimax H3 (24ch). Bypasses costly 5B-param VAE decode/encode. Upscale low-res latents directly, then refine. Accelerates high-res video gen, outperforms naive interp.
Upscale long, high-resolution MiniMax H3 video on a VRAM-limited GPU in a single node.
Generate large-scale explorable 3D scenes with high-quality panorama videos from a single image or text prompt.
Refine and improve the quality of small faces in MiniMax H3 video. Per-frame face tracking, crop, refine with H3, stitch back.
An experimental safe multimedia toolkit
Training-free Spectrum acceleration for ComfyUI’s native MiniMax H3 audio-video model. Uses Chebyshev ridge feature forecasting to skip selected H3 transformer evaluations, with adaptive scheduling…
Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++
A professional video editor with AI built in. Multi-track timeline, node-based generation workflows, and an integrated LLM assistant that can search your project, answer questions, and make edits f…
Build TensorRT engines from custom SDXL checkpoints for Sentinel.
Official implementation of Kimodo, a kinematic motion diffusion model for high-quality human(oid) motion generation.
Responsive photo gallery component for React
A simple local image and video UI for ComfyUI, without the graph editor.
Too Long, Didn't Read: Compress command output before it reaches your LLM. Save up to 99% of tokens without losing the signal.
The agent that grows with you
Fastest and only macOS Dictation app with on-device STT and custom trained AI enhancement model. Windows pre-build available! A local Wispr Flow alternative. DM us on X exclusive model access! 😉 - …
Typescript/React Library for AI Chat 💬🚀
Open source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for multitasking, organization, and programmability.
React Flow | Svelte Flow - Powerful open source libraries for building node-based UIs with React (https://reactflow.dev) or Svelte (https://svelteflow.dev). Ready out-of-the-box and infinitely cust…
Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference
Fast Rust port of Steve Yegge's beads: local-first, non-invasive issue tracker storing tasks in SQLite with JSONL export for git collaboration
Agent File (.af): An open file format for serializing stateful AI agents with persistent memory and behavior. Share, checkpoint, and version control agents across compatible frameworks.
Archived - has been replaced by Letta Code channels/schedules!
Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.