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

Build Better Websites. Create modern, resilient user experiences with web fundamentals.

Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.

LLM Frontend for Power Users.

The official API server for Exllama. OAI compatible, lightweight, and fast.

The Firefox theme with too many options.. FF Ultima.

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.

LLM inference in C/C++

All of source code of version 10 or later of Floorp Browser, the most Advanced and Fastest Firefox derivative 🦊

AI Agnostic (Multi-user and Multi-bot) Chat with Fictional Characters. Designed with scale in mind.

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

Accelerate, Optimize performance with streamlined training and serving options with JAX.

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Welcome to a calmer internet

A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

Large-scale LLM inference engine

💖🧸 Self hosted, you owned Grok Companion, a container of souls of waifu, cyber livings to bring them into our worlds, wishing to achieve Neuro-sama's altitude. Capable of realtime voice chat, Minec…

Run GGUF models easily with a KoboldAI UI. One File. Zero Install.

Making large AI models cheaper, faster and more accessible

a dark, customizable discord theme.

The full-stack JavaScript framework for SaaS apps.

Dockerized FastAPI wrapper for Kokoro-82M text-to-speech model w/CPU ONNX and NVIDIA GPU PyTorch support, handling, and auto-stitching

程序员在家做饭方法指南。Programmer's guide about how to cook at home (Simplified Chinese only).

把萌萌哒的看板娘抱回家 (ノ≧∇≦)ノ | Live2D widget for web platform

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.

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

Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚

Speech-to-text server framework with next-gen Kaldi

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…

The official gpt4free repository | various collection of powerful language models | o4, o3 and deepseek r1, gpt-4.1, gemini 2.5