microsoft/sre-agent

microsoft/sre-agent

Description: Azure SRE Agent is an AI-powered reliability assistant that helps teams diagnose and resolve production issues, reduce operational toil, and lower mean time to resolution

Language: Shell

License: MIT

Stars: 121

Forks: 59

Open issues: 68

Created: 2025-09-22T17:57:18Z

Pushed: 2026-06-19T05:45:37Z

Default branch: main

Fork: no

Archived: no

README:

Azure SRE Agent — Resources

This repository is the official community hub for Azure SRE Agent. Here you'll find:

• 🐛 Report Issues — File bugs, feature requests, and feedback via GitHub Issues
• 📚 Resources — Curated links to docs, videos, blogs, and community content for Azure SRE Agent
• 🧪 Labs — Hands-on labs and sample environments to deploy, break, and fix apps with Azure SRE Agent (see the [labs/](labs/) folder)

---

Quick Links

| Resource | Link | |----------|------| | Product Home Page | | | Portal (Create & Manage Agents) | | | Documentation | | | Pricing & Billing | | | All Blogs | | | YouTube Channel | | | GitHub — Azure SRE Agent (Report Issues, Official Labs & Resources) | | | Hands-on Lab | | | Request a New Region | | | GitHub — Official Plugins | | | Tech Community Discussions | | | Agentic DevOps Live | | | X (Twitter) | |

---

Featured Videos

Azure SRE Agent: End to End Agentic Operations Platform for Any Kind of Toil at Enterprise Scale

A comprehensive look at Azure SRE Agent as an end-to-end agentic operations platform — covering how it tackles every kind of operational toil and scales to meet enterprise needs. 🔗

What is Azure SRE Agent — Official Overview

The official Microsoft Azure product overview — a concise explainer of what Azure SRE Agent is, how it works, and the problems it solves. 🔗 · 6,156 views · 158 likes

Microsoft AI SRE Agent: Fixing Bugs While You Sleep

Satya Nadella highlights Azure SRE Agent as a key example of AI-driven operations transforming how engineering teams manage reliability at scale. 🔗 · 2,548 views · 26 likes

Azure SRE Agent: Less Toil, More Uptime, Maximum Innovation — Azure Friday

Scott Hanselman walks through Azure SRE Agent on Azure Friday, showing how it reduces operational toil and lets teams focus on innovation. 🔗 · 4,264 views · 75 likes

Root Cause Analysis with Code Context: Azure SRE Agent + GitHub Integration — GA Launch

The GA launch video demonstrating Azure SRE Agent performing root cause analysis with full code context through deep GitHub integration. 🔗 · 582 views · 25 likes

Use Azure SRE Agent to Automate Tasks and Increase Site Reliability (DEM550) — Build

Deep-dive Build session covering end-to-end SRE Agent capabilities: automated investigation, remediation, proactive monitoring, and custom hooks. 🔗 · 12,294 views · 129 likes

---

More Videos

• Fix It Before They Feel It: Proactive .NET Reliability with Azure SRE Agent — dotnet · 1,466 views
• Azure SRE Agent - Incident Management with PagerDuty — Azure SRE Agent (official) · 547 views
• Azure SRE Agent - Your 24/7 Automated Response Team — Mariusz Ferdyn · 313 views
• Azure's New SRE Agent Is INSANE — Here's Why you Should Pay Attention — TechTalks with Gil · 249 views
• SRE Agent Series: What Is Azure SRE Agent and How to Create One Step by Step — JBSWiki · 204 views
• Azure SRE Agent Explained — Cloud Talk with Jonnychipz · 160 views
• SRE Agent Series: I Let an Azure SRE Agent Manage My Subscription — Here's What Happened — JBSWiki · 143 views
• Agentic DevOps: Azure SRE Agent with GitHub Copilot Coding Agent demo — Jorge Balderas · new

---

Blogs

//Build 2026 (May 2026)

• [Azure SRE Agent at Microsoft //Build 2026](https://aka.ms/Build26/blog/SREAgent) — Headline //Build announcement and roadmap for what's next in Azure SRE Agent.
• [VNet Integration for Azure SRE Agent](https://aka.ms/sreagent/blog/VNET) — Secure private network connectivity so the agent can investigate workloads in locked-down VNets.
• [Hooks and Tool Permissions](https://aka.ms/sreagent/blog/HooksAndToolPermissions) — New governance controls to customize agent behavior and gate which tools it can use.
• [Private Plugin Marketplace](https://aka.ms/sreagent/blog/privatepluginmarketplace) — Publish and distribute internal plugins to your organization with full lifecycle management.
• [GitHub Enterprise Support](https://aka.ms/sreagent/blog/githubenterprise) — Native integration for GitHub Enterprise Cloud and GHE Server customers.
• [Connectors v2](https://aka.ms/sreagent/blog/connectorsv2) — Next-generation connector framework with improved auth, schema, and lifecycle.

//Build Session: Using autonomous SRE to move from alerts to action (OD800)

Post-GA (April 2026)

• [Event-Driven IaC Operations: Terraform Drift Detection via HTTP Triggers](https://techcommunity.microsoft.com/blog/appsonazureblog/event-driven-iac-operations-with-azure-sre-agent-terraform-drift-detection-via-h/4512233) — Vineela Suri · 10 min read. End-to-end pipeline: Terraform Cloud webhook triggers SRE Agent to classify drift as benign/risky/critical, correlate with incidents, and ship a fix — including a "DO NOT revert" recommendation that prevents turning a mitigated incident into an outage.
• [Managing Multi-Tenant Azure Resources with SRE Agent and Lighthouse](https://techcommunity.microsoft.com/blog/appsonazureblog/managing-multi%E2%80%91tenant-azure-resource-with-sre-agent-and-lighthouse/4511789) — Pranab Mandal · 6 min read. Step-by-step guide to configuring Azure Lighthouse delegation so a single SRE Agent can monitor and manage resources across multiple tenants — covering ARM templates, RBAC roles, and managed identity setup.
• [New in Azure SRE Agent: Log Analytics and Application Insights Connectors](https://techcommunity.microsoft.com/blog/appsonazureblog/new-in-azure-sre-agent-log-analytics-and-application-insights-connectors/4509649) — Dalibor Kovacevic · 3 min read. Native MCP-backed connectors for Log Analytics and App...