ai-sre 开源项目推荐（46 个）

mxsm /rocketmq-rust

Apache RocketMQ 基于 Rust 构建 🦀——更快、更安全、更节省内存。为 AI 时代提供高性能消息传递，具备 AI Agent、MCP 和 AI-SRE 能力。

derisk-ai /OpenDerisk

AI原生风险智能系统，OpenDeRisk——您的应用系统风险智能管理器提供7天24小时全面深入的保护。

incidentfox /incidentfox

AI 驱动的 SRE 平台，用于自动化事件调查

mezmo /aura

AURA 是经过生产验证的 SRE 智能体平台，几分钟内即可部署。AURA 负责将 AI 安全应用于生产基础设施所需的护栏、API、状态管理、流式处理和故障处理。

swapnildahiphale /OpenSRE

OpenSRE——记忆优先的 AI SRE。具备情景记忆、知识图谱、Web 控制台、Slack 和 Teams 的自托管事件调查。opensre.in

agamm /awesome-ai-sre

精选的 100+ 款 AI 驱动工具、平台和资源列表，面向站点可靠性工程（SRE）——包括智能体、事件管理、可观测性、AIOps、混沌工程等。

FluidifyAI /Regen

Open-source oncall management Alerts, Incidents, AI post-mortems. Self-hosted alternative to PagerDuty & incident.io. BYO-AI, Works with Prometheus, Grafana, Datadog, Slack, and Teams

pavangudiwada /awesome-ai-sre

AI SRE tools for RCA, Incident Response, Cost-Saving, Infra management, DevOps and more

glassflow /tares

Open-source platform for always-on AI agents: a software factory for Claude Code that takes your projects from tickets to merged pull requests, or an AI SRE that watches your systems.

incidentfox /OpenRag

Multi-strategy RAG system achieving 74% Recall@10 on MultiHop-RAG. Combines RAPTOR hierarchical retrieval, knowledge graphs, HyDE, BM25, and Cohere neural reranking.

aptible /unpage

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

MSKazemi /kubeintellect

An AI SRE for Kubernetes: connects to your cluster, investigates with real tools, explains the root cause in plain English, and executes the fix only after you approve it. Peer-reviewed — Journal of Grid Computing, 2026.

chatwoot /faultline

An open-source AI agent for infrastructure debugging.

talkops-ai /talkops

Open-Source AI Platform for DevOps, SRE, Cloud, and Platform Engineering

FireFightLabs /firefight

Open-source AI SRE and incident management. Finds the root cause and fixes it.

talkops-ai /k8s-autopilot

Open-source, extensible AI operations framework for Kubernetes. Autonomous multi-agent operators for Helm, GitOps & observability with no-code MCP plugins and rubric verification.

agentkourier /agent-kourier

Write the agent, not the chat integration. Kubernetes-native broker between Slack and streaming A2A AI agents (kagent, Google AX): threaded sessions, alert investigations, restart recovery.

talkops-ai /opscode

A terminal-native AI coding agent for DevOps, SRE, and Platform Engineering

ianwieds /awesome-agentic-devops

AI SRE and incident agents, infrastructure agents, CI/CD agents and the tools that let agents run operations.

MohamadKanso /IncidentForge

Synthetic production incidents and RCA evaluation for AI SRE agents.