I was on-call for a service once and got paged at 2am for a Kubernetes cluster that was falling apart in three different ways simultaneously. I spent 45 minutes running kubectl commands to understand what was happening before I could even start fixing it. InfraOS AI is my answer to that problem .
It's a DevOps operations platform that connects to your Kubernetes cluster, pulls in everything that's happening — pods, deployments, resource usage, events, Prometheus metrics — and gives you an AI layer to make sense of it all. You can ask "why is this pod crashing?" in plain English and get a real answer, not a wall of log output .
🛠️ What it does:
Cluster Monitoring — Live view of your nodes, pods, deployments, and services. Health status, restart counts, resource requests vs. limits.
Natural Language Queries — Ask questions like "Which pods have restarted more than 5 times in the last hour?" and it translates these into the right queries.
Root Cause Analysis — When something breaks, it traces back through events, logs, and metrics to figure out why.
Anomaly Detection — Watches your metrics over time and flags unusual patterns before they become incidents.
Automated Remediation — For common problems it can take action directly: restart a crashed pod, scale a deployment, or cordon a misbehaving node.
Mock Mode — No Kubernetes cluster? No problem. Set K8S_MOCK_MODE=true and it generates realistic fake cluster data for exploring the UI.
🧰 Tech Stack
Python, FastAPI, Kubernetes API, Prometheus, Grafana, Redis, PostgreSQL, and optional Ollama for local AI.
🔗 Get Started
Check out the repo: github.com/isidhartha/infra-os