Skip to main content
ClaudeWave

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。

Subagents2.7k stars546 forksJavaApache-2.0Updated 2d ago
Editor's note

Ragent is a Java-based, enterprise-grade Agentic RAG platform built with Spring AI that covers the full pipeline from document ingestion to intelligent question answering. It implements parallel multi-channel retrieval with deduplication and reranking, a tree-structured intent classifier that requests clarification when confidence falls below a threshold, query rewriting for multi-turn conversations, session memory management, and MCP tool integration that automatically invokes business tools for non-knowledge intents. The platform includes a model scheduling layer with health checks, first-packet latency probing, and automatic failover so that individual model outages do not interrupt service. It connects to LLMs through a custom scheduling engine rather than LangChain4j or Spring AI abstractions, a deliberate design choice the project documents in detail. The primary audience is Java backend developers transitioning into AI engineering roles, and the repository explicitly frames the codebase as resume-ready material for candidates who need to demonstrate production-grade RAG and Agent experience in technical interviews.

ClaudeWave Trust Score
100/100
Verified
Passed
  • Open-source license (Apache-2.0)
  • Actively maintained (<30d)
  • Healthy fork ratio
  • Clear description
  • Topics declared
  • Documented (README)
Last scanned: 6/11/2026
Install as a Claude Code subagent
Method: Clone
Terminal
git clone https://github.com/nageoffer/ragent && cp ragent/*.md ~/.claude/agents/
1. Clone the repository and copy the agent .md definitions into ~/.claude/agents (or .claude/agents inside a project).
2. Start a new Claude Code session to load the agents.
3. Delegate work to them with the Task/Agent tool or by name.
Use cases

Subagents overview

README preview not available. Visit the repo on GitHub for full documentation.
agentagentic-ragaillmmcpragspringai

What people ask about ragent

What is nageoffer/ragent?

+

nageoffer/ragent is subagents for the Claude AI ecosystem. 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。 It has 2.7k GitHub stars and was last updated 2d ago.

How do I install ragent?

+

You can install ragent by cloning the repository (https://github.com/nageoffer/ragent) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.

Is nageoffer/ragent safe to use?

+

Our security agent has analyzed nageoffer/ragent and assigned a Trust Score of 100/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.

Who maintains nageoffer/ragent?

+

nageoffer/ragent is maintained by nageoffer. The last recorded GitHub activity is from 2d ago, with 25 open issues.

Are there alternatives to ragent?

+

Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.

Deploy ragent to your cloud

Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.

Maintain this repo? Add a badge to your README

Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.

Featured on ClaudeWave: nageoffer/ragent
[![Featured on ClaudeWave](https://claudewave.com/api/badge/nageoffer-ragent)](https://claudewave.com/repo/nageoffer-ragent)
<a href="https://claudewave.com/repo/nageoffer-ragent"><img src="https://claudewave.com/api/badge/nageoffer-ragent" alt="Featured on ClaudeWave: nageoffer/ragent" width="320" height="64" /></a>

More Subagents