Dify-Plus 是面向企业场景的 Dify 开源增强版,基于 Dify 原生架构,提供 Casdoor 单点登录、统一系统管理、用户额度、API 密钥限额和应用中心等功能,无需单独部署管理后台。🚀 本项目为社区二次开发成果,遵循 Dify 原项目的开源许可证及版权要求。涉及商业授权、多租户服务或品牌使用等需求,请以 Dify 官方许可条款为准,并联系官方获取相应授权与支持。
Repository Index
89,572 visible repositories in the index
6,313–6,336 of 15,401 · Most stars
Aix-DB 基于 LangChain/LangGraph 框架,结合 MCP Skills 多智能体协作架构,实现自然语言到数据洞察的端到端转换。
Spectral simulation of analog photography processes
Web Crawling and RAG Capabilities for AI Agents and AI Coding Assistants
Ongoing research training transformer language models at scale, including: BERT & GPT-2
AIWriteX - 微信公众号全自动AI工具:全网热搜舆情聚合+趋势分析+爆款选题+文章采集+一键生成排版发布 | AI自动配图 | 去AI味、过朱雀检测 | 支持小红书/百家号/头条等多平台 | 洗稿润色支持多账号 | 专家赛道 | 小绿书贴图 | 短视频文案 | 手机控制 | 小说连载 | 短剧剧本 | 爆文10w+神器
- crewai
- weixin
- wx
- ai-wx
The repository host gives no description.
This curated list contains python packages for time series analysis
Prompts, workflows and more for agentic engineering
GlobalBuildingAtlas: an open global and complete dataset of building polygons, heights and LoD1 3D models
Tracking Any Point (TAP)
- benchmark
- point-tracking
- robotics
- computer-vision
Python package for scraping recipes data
- data-extraction
- food
- html-parsing
- json-ld
The implementation of DeBERTa
- bert
- deeplearning
- representation-learning
- roberta
[TPAMI 2026🔥] Helios: Real Real-Time Long Video Generation Model
- acceleration
- diffusion
- diffusion-models
- image-to-video
This repository is deprecated and will be archived
Example code from the book
📺 An End-to-End Solution for High-Resolution and Long Video Generation Based on Transformer Diffusion
Chinese Named Entity Recognition with IDCNN/biLSTM+CRF, and Relation Extraction with biGRU+2ATT 中文实体识别与关系提取
- nlp
- chinese-nlp
- information-extraction
- relation-extraction
A website displaying hundreds of charts made with Python
Unsupervised single image depth prediction with CNNs
小白的Python入门教程实战篇:网站+iOS App源码
- python
- python3
Weblogic一键漏洞检测工具,V1.5,更新时间:20200730
- weblogicscan
micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape
- quantization
- pruning
- dorefa
- twn
AI PPT赛道终结者,史上最最最强 PPT Skill!!! 使用GPT生成豪华的图片格式PPT,然后转换为完全可编辑的PPTX文件。