ongridio/ongrid
Ongrid is an AI-powered ops agent that autonomously investigates alerts, performs root-cause analysis, and orchestrates fixes for IT infrastructure issues, interacting via chat platforms.
Awesome AI for Infra › Incident Management & Response
olemeyer/rocketplaneIO
rocketplaneIO is an open-source, self-hosted AI SRE platform designed for Kubernetes environments, emphasizing safety and control. It offers zero-instrumentation observability using eBPF, collecting HTTP/gRPC spans with cross-service context propagation, SQL, Redis, and Kafka client spans without code changes or SDKs. The core innovation is an AI Copilot that autonomously investigates incidents and proposes solutions. Unlike general-purpose AI tools, rocketplaneIO's Copilot interacts with the cluster exclusively through a catalog of approximately 30 named, reversible action pipelines, preventing direct `kubectl` or YAML hallucination. Each action is risk-graded, with configurable approval levels from read-only to destructive, ensuring that the model proposes but deterministic pipelines execute, verify at the pod level, and roll back automatically upon failure. The platform supports bring-your-own-LLM, including local and air-gapped models, ensuring telemetry stays within the user's infrastructure. It includes an audit trail for all actions, allowing one-click reverts to the state before a change. Security features include outbound-only agents, robust authentication, enumerated RBAC, and strict handling of secrets. Currently in alpha, it offers a quick start with Docker Compose and supports connecting existing Kubernetes clusters.
https://github.com/olemeyer/rocketplaneIO
Also in Incident Management & Response
Tommy-yw/RunbookHermes
RunbookHermes is an AIOps agent built on the Hermes Agent framework, designed for evidence-driven incident response, approval-gated remediation, and self-evolving runbook learning.
Arvo-AI/aurora
Aurora is an open-source, AI-powered incident management platform that uses AI agents to autonomously investigate incidents, perform root cause analysis, and suggest remediations across multi-cloud...
swapnildahiphale/OpenSRE
OpenSRE is an open-source AI SRE agent that automates incident investigation, root cause analysis, and learns from past incidents using episodic memory and a knowledge graph.
papadopouloskyriakos/agentic-chatops
This project implements a multi-agent ChatOps system that uses AI/ML to autonomously triage, investigate, and propose fixes for infrastructure alerts, including self-improving prompts and a causal ...