Lists (2)
Stars
The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.
PDF generation with JSX. Page breaks that actually work.
TerraInk: The Cartographic Poster Engine that creates unique and customizable map posters
Fun-Audio-Chat is a Large Audio Language Model built for natural, low-latency voice interactions.
A next.js web application that integrates AI capabilities with draw.io diagrams. This app allows you to create, modify, and enhance diagrams through natural language commands and AI-assisted visual…
Implementation of Q-learning to solve GridWorld
Plug-and-play memory for LLMs in 3 lines of code. Add persistent, intelligent, human-like memory and recall to any model in minutes.
🔥 The Web Data API for AI - Power AI agents with clean web data
[ICLR'26] The official code implementation for "Cache-to-Cache: Direct Semantic Communication Between Large Language Models"
Official MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.
A comprehensive ComfyUI integration for Microsoft's VibeVoice text-to-speech model, enabling high-quality single and multi-speaker voice synthesis directly within your ComfyUI workflows.
VibeVoice: Expressive, longform conversational speech synthesis. (Community fork)
VoXtream is a Full-Stream Zero-shot TTS model with Extremely Low Latency and Speaking rate Control
Unofficial WIP LoRa Finetuning repository for VibeVoice
Recursive-Open-Meta-Agent v0.1 (Beta). A meta-agent framework to build high-performance multi-agent systems.
Reference PyTorch implementation and models for DINOv3
Easily train a good VC model with voice data <= 10 mins!
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
Kimi K2 is the large language model series developed by Moonshot AI team
A high-throughput and memory-efficient inference and serving engine for LLMs
Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.
Official inference framework for 1-bit LLMs
An open-source AI agent that brings the power of Gemini directly into your terminal.
FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI…