Kkkirito-123

Kkkirito-123 / mutil-rag-agent

Public

An improved multi-agent AIOps and RAG platform for OnCall troubleshooting, featuring LangGraph-based diagnosis workflows, Milvus vector search, MCP tool integration, Prometheus alert knowledge from awesome-prometheus-alerts, and sanitized configuration for safe public deployment.

13
1
100% credibility
Found May 07, 2026 at 13 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

AI platform that diagnoses IT issues like high CPU, memory shortages, or disk problems using agents that plan steps, check systems, and generate reports.

How It Works

1
👀 Discover your IT helper

You hear about this smart assistant that diagnoses computer glitches like slow performance or full disks from a video demo.

2
🚀 Launch it easily

You start the helper with one simple click, and it sets up your personal troubleshooting doctor.

3
📚 Load fix guides

You add ready-made guides on common issues so the assistant knows proven steps to check.

4
🔔 Describe your alert

You simply type what went wrong, like 'My computer is lagging with high memory use'.

5
🔍 Watch it investigate

The assistant chooses a strategy, checks your system live, and shows each clue it finds.

✅ Receive your solution

You get a clear report explaining the cause and exact steps to fix it, turning chaos into calm.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 13 to 13 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is mutil-rag-agent?

This Python-based multi-agent AIOps platform automates on-call troubleshooting by ingesting Prometheus alerts via webhook, running LangGraph diagnosis workflows, and delivering structured reports. It combines RAG for Milvus-powered knowledge retrieval with MCP-integrated tools for real-time system checks like CPU, logs, and Docker stats, pulling alert patterns from awesome-prometheus-alerts. Users get a docker-compose deployment with sanitized configuration for safe public setup, plus a chat interface for follow-up queries.

Why is it gaining traction?

It stands out with improved multi-agent collaboration via plan-execute-replan cycles, handling complex diagnosis better than single-agent setups, while hybrid search boosts recall on error codes and metrics. The seamless Prometheus webhook turns alerts into async diagnoses stored in history files, saving SREs hours on triage. Easy deployment and agent tool integration make it a quick win for aiops experimentation.

Who should use this?

On-call SREs drowning in Prometheus alerts from services like Redis or Kubernetes pods. DevOps teams building automated diagnosis pipelines, especially those already using Milvus or awesome-prometheus-alerts rules. Not for production without custom tweaks—ideal for prototyping improved multi-agent path finding in incident response.

Verdict

Grab it if you're prototyping aiops agents; the 1.0% credibility score and 13 stars signal early-stage code needing more tests and docs. Solid for alert diagnosis demos, but audit configs before real alerts hit.

(187 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.