[NeurIPS 2025] Radial Attention: O(n\log n) Sparse Attention with Energy Decay for Long Video Generation

Mochi is a proof-of-concept C++ loader that leverages the ChaiScript embedded scripting language to execute code.

Create flashcards on Mochi.cards using the API provided by Mochi's Pro subscription in Obsidian.

Based on Dasai™ Mochi

Convert your Notion database to Mochi cards.

Like Anki's Review Heatmap, but for Mochi Cards!

WhatsAI - An easy-to-use UI fully based on ComfyUI.

Serve Text-to-Video Models in Production

generate videos with open source ai models

Front-end framework for developing responsive, mobile-first projects on the web or offline.

One-way synchronization of flashcards from Logseq to Mochi

Generate videos with Mochi as an endpoint on RunPod

Benchmarking training throughput of contemporary diffusion models on AMD's GPU hardware.

A pen-and-paper based, efficient and scalable spaced repetition system.

A simple cmd line tool to help you practice kanjis from your Mochi cards. (for private use).

try mochi

ESP32 client for the GenAI Mochi animatronics project

Front-end framework for developing responsive, mobile-first projects on the web or offline.

Study computer science funamentals like data structures and algorithms with Quizlet + Mochi flashcards 🧠⚡

A high-performance, GPU-optimized real-time speech-to-text (STT) streaming server built with WebSocket support for multiple concurrent clients. This project leverages the Kyutai STT model and is optimized for NVIDIA RTX 4090 GPUs, providing low-latency transcription for audio streams.