memobase

Profile-Based Long-Term Memory for AI Applications. Memobase handles user profiles, memory events, and evolving context — perfect for chatbots, companions, tutors, customer service bots, and all chat-based agents.

PIKE-RAG

PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation

Local-File-Organizer

An AI-powered file management tool that ensures privacy by organizing local texts, images. Using Llama3.2 3B and Llava v1.6 models with the Nexa SDK, it intuitively scans, restructures, and organizes files for quick, seamless access and easy retrieval.

AsrTools

**注意：更多强大功能已经在我另一个项目实现:** VideoCaptionerhttps://github.com/WEIFENG2333/VideoCaptioner 基于 LLM 的智能字幕助手，无需GPU一键高质量字幕视频合成！支持生成、断句、优化、翻译全流程。让视频字幕制作简单高效！ 🎤 AsrTools 🌟 **特色功能** - 🚀 **无需复杂配置**：无需 GPU 和繁琐的本地配置，小白也能轻松使用。 - 🖥️ **高颜值界面**：基于 **PyQt5** 和 **qfluentwidgets**，界面美观且用户友好。 - ⚡ **效率超人**：多线程并发 + 批量

o1-engineer

o1-engineer is a command-line tool designed to assist developers in managing and interacting with their projects efficiently. Leveraging the power of OpenAI's API, this tool provides functionalities such as code generation, file editing, and project planning to streamline your development workflow.

fluxgym

Dead simple FLUX LoRA training UI with LOW VRAM support

LLaMA-Omni

LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.

AI-Guide-and-Demos-zh_CN

这是一份入门AI/LLM大模型的逐步指南，包含教程和演示代码，带你从API走进本地大模型部署和微调，代码文件会提供Kaggle或Colab在线版本，即便没有显卡也可以进行学习。项目中还开设了一个小型的代码游乐场🎡，你可以尝试在里面实验一些有意思的AI脚本。同时，包含李宏毅 (HUNG-YI LEE）2024生成式人工智能导论课程的完整中文镜像作业。

seed-vc

Seed-VC *English | 简体中文README-ZH.md | 日本語README-JA.md* real-time-demo.webmhttps://github.com/user-attachments/assets/86325c5e-f7f6-4a04-8695-97275a5d046c Currently released model supports *zero-shot voice conversion* 🔊 , *zero-shot real-time voice conversion* 🗣️ and *zero-shot singing voice

mochi

The best OSS video generation models, created by Genmo

Nugget

Unlock the fullest potential of your device

g1

g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains