Skip to content

About

Hand it the logs from a bad night and get back the likely root cause, similar incidents from the past, and the commands to fix it. Seven LangGraph agents split the work, and nothing risky runs until a human says yes.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Repository files navigation

AI DevOps Logo

AI DevOps & Cloud Incident Assistant

An Enterprise-Grade, Multi-Agent Platform for Automated DevOps Incident Analysis & Remediation

React FastAPI PostgreSQL LangChain


🚀 Overview

The AI DevOps & Cloud Incident Assistant is a flagship open-source incident management platform. It leverages advanced Multi-Agent AI orchestration via LangGraph and the Model Context Protocol (MCP) to ingest, analyze, and automatically resolve complex server and cloud application incidents.

Unlike standard "log viewers" or simple LLM wrappers, this platform operates autonomously using a crew of specialized AI agents working together to perform Root Cause Analysis (RCA), query historical knowledgebases via RAG, and generate safe, actionable CLI commands to fix issues in real-time.

✨ Key Features

  • 🧠 Multi-Agent Orchestration: Seven specialized LangGraph agents (Coordinator, Parser, RCA, RAG, Recommendation, Command Gen, Report Gen).
  • 🛠 Model Context Protocol (MCP): Native integration for AI tool execution.
  • 🔍 Explainable AI: Provides confidence scoring, alternative root causes, and visual business impact analysis.
  • 🛡️ Human-in-the-Loop Security: Strict approval workflows before dangerous command execution.
  • 💾 Persistent AI Memory: Context-aware recommendations that learn from past user feedback and incidents.
  • 📊 Real-time Dashboard: Beautiful glassmorphic UI visualizing system health, incidents, and logs instantly.
  • 🎓 Interactive Lab: Simulate complex database timeouts, OOM errors, and network failures in a sandbox environment.

🏗️ Architecture

  1. Log Ingestion: Raw application logs stream into the FastAPI backend and are stored in PostgreSQL.
  2. LangGraph Pipeline: A Coordinator Agent delegates logs to specialized sub-agents.
  3. Reasoning & RAG: The Root Cause Analyzer references ChromaDB for similar past incidents using semantic search.
  4. Resolution: The Recommendation Agent creates actionable remediation commands.
  5. UI Layer: React/Tailwind frontend fetches the structured telemetry to display in a premium interface.

💻 Tech Stack

  • Frontend: React (Vite), Tailwind CSS v4, Framer Motion, Recharts, React Flow.
  • Backend: FastAPI, SQLAlchemy, WebSockets, Python 3.13.
  • AI / Agentic Frameworks: LangGraph, LangChain, ChromaDB, Sentence-Transformers, Llama 3.1 (via Groq).
  • Infrastructure: Docker Compose (PostgreSQL, Vector DB).

🛠️ Quick Start

1. Environment Configuration

Copy the sample environment file and configure your GROQ_API_KEY.

cd backend
cp .env.example .env

2. Start Infrastructure

Launch the PostgreSQL and ChromaDB containers:

docker-compose up -d

3. Start the Backend

cd backend
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
uvicorn main:app --reload

4. Start the Frontend

cd frontend
npm install
npm run dev

Navigate to http://localhost:5173 to view the Dashboard!


Created by Kaushik
Designed for next-generation Cloud & SRE teams.

About

Hand it the logs from a bad night and get back the likely root cause, similar incidents from the past, and the commands to fix it. Seven LangGraph agents split the work, and nothing risky runs until a human says yes.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages