Stars
A curated collection of fun and creative examples generated with Nano Banana🍌, Gemini-2.5-flash-image based model. We also release Nano-consistent-150K openly to support the community's development…
A modular graph-based Retrieval-Augmented Generation (RAG) system
Fully local web research and report writing assistant
The Open-Source Agentic Workspace for Human-AI Collaboration.
Trae Agent is an LLM-based agent for general purpose software engineering tasks.
🦜🔗 The platform for reliable agents.
🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)
🤩 Easy-to-use global IM bot platform designed for LLM era / 简单易用的大模型即时通信机器人开发平台 ⚡️ Bots for QQ / QQ频道 / Discord / LINE / WeChat(微信, 企业微信)/ Telegram / 飞书 / 钉钉 / Slack 🧩 Integrated with ChatGPT(GPT),…
Generative Agents: Interactive Simulacra of Human Behavior
Web Extension for saving a faithful copy of a complete web page in a single HTML file
基于大模型搭建的聊天机器人，同时支持 微信公众号、企业微信应用、飞书、钉钉 等接入，可选择ChatGPT/Claude/DeepSeek/文心一言/讯飞星火/通义千问/ Gemini/GLM-4/Kimi/LinkAI，能处理文本、语音和图片，访问操作系统和互联网，支持基于自有知识库进行定制企业智能客服。
AI-First Album: Chat with your gallery using plain language! LLM Vision + RAG + Album/Gallery.
Reproducing images with geometric primitives.
Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation
MediaCMS is a modern, fully featured open source video and media CMS, written in Python/Django and React, featuring a REST API.
A simple library and set of tools for parsing, modifying, and composing SRT files.
Discord4J is a fast, powerful, unopinionated, reactive library to enable quick and easy development of Discord bots for Java, Kotlin, and other JVM languages using the official Discord Bot API.
An open-source AI avatar generator web app - https://photoshot.app
Controllable and fast Text-to-Speech for over 7000 languages!
YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone
Tacotron 2 - PyTorch implementation with faster-than-realtime inference
🔊 Text-Prompted Generative Audio Model
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
Instant voice cloning by MIT and MyShell. Audio foundation model.