nageoffer/ragentMCPMCP Server

ragent

企业级 Agentic RAG 智能体 - 全链路覆盖文档解析、多路检索、意图识别、问题重写、会话记忆、MCP 工具调用与深度思考。面向真实业务场景，从 0 到 1 完整工程实现。

2.6kstars

510forks

Java

agentagentic-ragaillmmcpragspringai

Quality signals

ActiveNo testsNo CIThin docsNo licensePopular

Open Repository Download ZIP

AI summary

Auto-generated overview of what this skill does and when to reach for it.

Enterprise-grade Agentic RAG system handling full pipeline from document parsing to multi-path retrieval, intent recognition, query rewriting, conversation memory, MCP tool calls, and deep reasoning for real business scenarios.

Use this when

Need to parse and index enterprise documents (PDFs, Word, PPT) for AI retrieval
Building AI agents that must handle multi-turn conversations with memory
Integrating external tools via MCP for non-knowledge tasks
Deploying RAG systems with model routing and failover for reliability
Debugging complex RAG pipelines with detailed execution logs

Don't use when

Quick prototyping with minimal setup
Simple chatbots without document retrieval needs
Projects requiring only basic keyword search

Capabilities

Multi-path retrieval with deduplication and re-ranking
Intent recognition with multi-level classification and confidence thresholds
Model routing with health checks and automatic failover
MCP tool integration for non-knowledge task execution
Document ingestion pipeline with configurable processing nodes
Conversation memory with context compression and persistence

Install

Universal installANY TOOL

$ npx skillcity@latest nageoffer/ragent

Auto-detects the skill or MCP server in this repo and installs it for Claude Code, Codex, Cursor or Cline.

Requires Node.js 18+ (ships with npx).

Prefer to set it up by hand? Clone the repository:

git clone https://github.com/nageoffer/ragent.git

Loading README…

Discover the toolingbehind modern intelligence

ragent