基于ragflow二次开发的后台管理系统,可以独立运行,支持批量管理知识库、聊天、智能体、用户等,解决ragflow在后台管理上的痛点。
<div align="center">
<a href="https://github.com/infiniflow/ragflow">
<img src="web/public/logo.svg" width="120" alt="RAGFlow logo">
</a>
<h1>RAGFlow Admin</h1>
</div>
<p align="center">
<a href="./README.md">English</a> |
<a href="./README_zh.md">简体中文</a>
</p>
<p align="center">
<a href="https://github.com/tedhappy/ragflow-admin/releases/latest">
<img src="https://img.shields.io/github/v/release/tedhappy/ragflow-admin?color=blue&label=Latest%20Release" alt="Latest Release">
</a>
<a href="https://github.com/infiniflow/ragflow">
<img src="https://img.shields.io/badge/RAGFlow-v0.15+-blue" alt="RAGFlow Version">
</a>
<a href="https://github.com/tedhappy/ragflow-admin/blob/main/LICENSE">
<img src="https://img.shields.io/badge/License-Apache%202.0-green" alt="License">
</a>
</p>
<p align="center">
A standalone administration console for RAGFlow
</p>
---
## 🔎 Overview
**RAGFlow Admin** is a lightweight, standalone administration console for [RAGFlow](https://github.com/infiniflow/ragflow) — the leading open-source RAG engine with deep document understanding. It provides a modern web interface for centralized management of datasets, documents, chat assistants, agents, and users.
### Why RAGFlow Admin?
RAGFlow is a powerful RAG engine, but its built-in management interface has some limitations for production use:
| Pain Point | RAGFlow Admin Solution |
|------------|------------------------|
| **Single dataset view** | Cross-dataset dashboard for unified management |
| **No batch operations** | Bulk upload, parse, stop, and delete across datasets |
| **Hidden task queue** | Real-time task monitoring with queue position and progress |
| **Complex user management** | Centralized user admin panel with statistics |
| **Limited operational insight** | Dashboard with health checks and usage metrics |
| **Steep learning curve** | Intuitive UI designed for administrators |
## ✨ Features
### Core Management
| Feature | HAL 分层混合模型工作流 — 强模型(Claude)负责理解/拆解/验收,低成本模型(DeepSeek)负责检索/提取/清洗。Hermes Agent skill。
An LLM agent fine-tuned on DeepSeek for spaced repetition, dynamically integrating knowledge points based on the Ebbinghaus forgetting curve.
基于 STM32F103 构建的端到端 AI 智能手表生态。自研“零重定位”原生机器码动态加载引擎与页面栈式 UI 框架;集成生产级 OTA 回滚保护机制与高带宽(921600 baud)串口协议栈。通过 Node.js 中继实现 DeepSeek AI 语义控制及 ASRPRO 语音全双工交互,是一个集成了分布式计算、现代存储管理与 AI Agent 的嵌入式全栈工程。
A Meta-Agent-Driven Self-Evolving Multi-Agent System for UAV Detection and Tracking
One command to run Hermes AI Agent with a browser UI. Zero prerequisites. 一行命令,AI 就位。
网页应用Agent,接入DeepSeek、Mimo等模型