User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

A high-throughput and memory-efficient inference and serving engine for LLMs

AIHawk aims to easy job hunt process by automating the job application process. Utilizing artificial intelligence, it enables users to apply for multiple jobs in a tailored way.

Contexts Optical Compression

A TTS model capable of generating ultra-realistic dialogue in one pass.

Fully automatic censorship removal for language models

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

Lets make video diffusion practical!

AI Agent Framework, the Pydantic way

Knowledge Engine for AI Agent Memory in 6 lines of code

A Conversational Speech Generation Model

State-of-the-art TTS model under 25MB 😻

structured outputs for llms

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

Towards Human-Sounding Speech

Download 'TIDAL' Music On Windows/Linux/MacOs (PYTHON/C#)

RAG that intelligently adapts to your use case, data, and queries

Have a natural, spoken conversation with AI!

🎚️ Open Source Audio Matching and Mastering

GraphRAG using Local LLMs - Features robust API and multiple apps for Indexing/Prompt Tuning/Query/Chat/Visualizing/Etc. This is meant to be the ultimate GraphRAG/KG local LLM app.

A powerful tool that translates ComfyUI workflows into executable Python code.

📺 An End-to-End Solution for High-Resolution and Long Video Generation Based on Transformer Diffusion

Code and model to control the AH!

Make text LLMs listen and speak

a security scanner for custom LLM applications

Lumina-mGPT 2.0: Stand-Alone AutoRegressive Image Modeling

LoRA Manager for ComfyUI - A powerful extension for organizing, previewing, and integrating LoRA models with metadata and workflow support.

Not supported. Measure 8 EEG channels with Shield PiEEG and RaspberryPi in C library