gaurav19gawade

AI Incident Agent — AI skill for Claude Code

AI community

AI-powered incident response agent built with Spring Boot and Claude AI.

How to install AI Incident Agent

This entry records only its repository, not the path inside it, so there is no exact command to give. Open gaurav19gawade/ai-incident-agent and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What AI Incident Agent does

AI-powered incident response agent built with Spring Boot and Claude AI. Automatically investigates, diagnoses, and remediates incidents across microservices using Kafka event streaming, PostgreSQL, Prometheus metrics, and Grafana dashboards.

Alternatives in AI

  • Botmux — Bridge Feishu/Lark to AI coding CLIs — Claude Code, Codex, Gemini, OpenCode… every DM, group or topic spawns i 1.2k ★
  • My Free Code — Open-source multi-provider AI gateway for Claude Code and other coding agents, with model routing, streaming 633 ★
  • GPT Image2 Ecommerce — GPT-Image-2 驱动的电商素材一键生成 Claude Code Skill E-commerce image generation skill powered by GPT-Image-2 via Codex C 332 ★

README

AI Incident Response Agent

An AI-powered incident response system that automatically investigates, diagnoses, and remediates production incidents in a distributed microservices environment. Built with Spring Boot and Claude AI (Anthropic), it uses a tool-calling agentic loop to query live metrics, traces, logs, and database stats — then generates a prioritised remediation plan with a human-in-the-loop approval workflow.

Architecture Overview

┌─────────────────────────────────────────────────────────────────┐
│                        incident-agent :8083                      │
│                                                                   │
│  ┌─────────────┐   ┌──────────────┐   ┌──────────────────────┐  │
│  │ AgentService │──▶│ ClaudeClient │──▶│   Anthropic API      │  │
│  │ (agentic     │   │ (tool-use    │   │   (claude-sonnet)    │  │
│  │  loop ≤12)   │◀──│  loop)       │◀──│                      │  │
│  └──────┬───────┘   └──────────────┘   └──────────────────────┘  │
│         │ calls                                                    │
│  ┌──────▼──────────────────────────────────────────────────────┐  │
│  │                    Tool Registry (9 tools)                   │  │
│  │  service_health  chaos_status  prometheus_query  kafka_lag   │  │
│  │  database_stats  jaeger_traces  search_runbooks              │  │
│  │  search_past_incidents  record_remediation_plan              │  │
│  └──────┬──────────────────────────────────────────────────────┘  │
└─────────┼───────────────────────────────────────────────────────┘
          │ HTTP
┌─────────▼──────────────────────────────────────────────────────┐
│                       Infrastructure                             │
│                                                                  │
│  order-service:8080 ──▶ inventory-service:8081                  │
│         │                      │                                 │
│         └──── Kafka ───────────┘                                 │