Stars
Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.
No fortress, purely open ground. OpenManus is Coming.
利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.
⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载，你的 AI 舆情监控助手与热点筛选工具！聚合多平台热点 + RSS 订阅，支持关键词精准筛选。AI 智能筛选新闻 + AI 翻译 + AI 分析简报直推手机，也支持接入 MCP 架构…
AiLearning：数据分析+机器学习实战+线性代数+PyTorch+NLTK+TF2
FauxPilot - an open-source alternative to GitHub Copilot server
Mobile-Agent: The Powerful GUI Agent Family
The most powerful Android RPA agent framework, next generation of mobile automation robots.
Officially maintained, supported by PaddlePaddle, including CV, NLP, Speech, Rec, TS, big models and so on.
AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.
Red Ink - A one-stop Xiaohongshu image-and-text generator based on the 🍌Nano Banana Pro🍌, "One Sentence, One Image: Generate Xiaohongshu Text and Images."
CNN-RNN中文文本分类，基于TensorFlow
A Simple and Versatile Framework for Object Detection and Instance Recognition
Fast and accurate human pose estimation in PyTorch. Contains implementation of "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose" paper.
A minimal yet professional single agent demo project that showcases the core execution pipeline and production-grade features of agents.
A ComfyUI custom node designed for advanced image background removal and object, face, clothes, and fashion segmentation, utilizing multiple models including RMBG-2.0, INSPYRENET, BEN, BEN2, BiRefN…
一个集内容策划、AI文案自动生成、TTS 批量自动配音、(AI)图片素材合成、ASR自动提取语言字幕脚本、AI自由创作于一体的(短视频)生成工作站。方便管理每期的视频项目。
Added vLLM support to IndexTTS for faster inference.
MXNet port of SSD: Single Shot MultiBox Object Detector. Reimplementation of https://github.com/weiliu89/caffe/tree/ssd
使用IndexTTS模型在ComfyUI中实现高质量文本到语音转换的自定义节点。支持中文和英文文本，可以基于参考音频复刻声音特征。
核心代码开源，电商、社交多平台自动AI智能客服机器人，支持多种平台（微信、拼多多、千牛、抖店、京东、企业微信、微博、小红书、知乎等平台接入）可接入任何模型（gpt、glm、千问、gemma、llama、qwen、phi、yi等）
CosyVoice2 功能扩充（预训练音色推理/3s极速复刻/自然语言控制/自动识别/音色模型保存/API）