sre-agent

Open-source, self-hosted alerting for metrics, logs, and databases. Includes a built-in AI agent and MCP server.

AI-powered SRE platform — read-only infrastructure diagnostics with deep investigation, security governance, and team collaboration

OpenSRE — the memory-first AI SRE. Self-hosted incident investigation with episodic memory, knowledge graph, web console, Slack & Teams. opensre.in

Unpage is the open source framework for building SRE agents with infrastructure context and secure access to any dev tool.

GitAGU (Git Agent Unblock) - A centralized platform for discovering, configuring, and integrating AI agents into your development workflow. Simplifies AI adoption across the entire Software Development Life Cycle

Agentic Operations & Observability Workshop: Hands-on guide for implementing AI-enhanced observability in cloud apps using Azure Monitor, Application Insights, and Azure SRE Agent. Covers metrics, logs, traces, multi-cloud monitoring, and agentic DevOps best practices.

Observes telemetry errors, maps root causes, and generates safe executable runbooks for production incident mitigation

Observes telemetry errors, maps root causes, and generates safe executable runbooks for production incident mitigation

An on-call oriented agent that turns Prometheus/Alertmanager alerts into actionable triage reports.

DEPRECATED: AKS Skills moved to the azure-skills marketplace (aks-skills@azure-skills). Source: microsoft/GitHub-Copilot-for-Azure

End goal is something similar to Jarvis from Iron Man. A complete assistant that can do anything.

Integration playbook unifying Azure, Developer Hub, and GitHub to revolutionize developer experience through advanced platform engineering. Features comprehensive architectures, guides, and templates for building a seamless development ecosystem.

Finalist @ Softserve Agent X Hackathon - Autonomous SRE agent that ingests incident reports for an e-commerce platform, performs AI-powered triage by analyzing the actual source code, and routes issues through a complete ticketing workflow with real-time notifications

An autonomous SRE assistant that detects, analyzes, and resolves production system issues through AI-powered multimodal interaction. Built with Next.js, Firebase, Google Cloud, and Gemini 1.5 Flash.

Autonomous SRE & DevOps Memory Agent - Google Cloud Rapid Agent Hackathon (MongoDB Atlas Track)

Two-app AKS demo for Azure SRE Agent auto-triage (5xx surge + CPU spike). One-shot deploy.sh, ~10 min, ~$2/day.