I'm creating opensource AWS DevOps Agent for SRE on-call engineers LLM root-cause hypothesis).
Day 1/100. For the past two months, I’ve been building an open-source tool for on-call engineers in my spare time. When a Kubernetes alert fires, it automatically gathers context and sends a hypothesis about the "why" to Telegram, complete with evidence and a way to verify if the hypothesis is incorrect. By design, it doesn't touch anything in the cluster. Yesterday, I ran it on a real EKS…
During the past two months, a developer has been working on an open-source tool aimed at aiding on-call engineers in handling Kubernetes alerts. This tool, named SentinelOps, was created in the developer's personal time. Upon triggering a Kubernetes alert, SentinelOps automatically compiles context and provides a hypothesis for the issue, accompanied by evidence and a verification method, without making any changes to the cluster.
In a recent test on a live EKS cluster, the tool's cost amounted to 13 cents. The developer evaluated the tool's accuracy, noting that the local model correctly identified the root cause in 5 out of 7 challenging situations, whereas the cloud model successfully resolved all 6 instances correctly. The developer is seeking a brief conversation with on-call engineers who utilize Kubernetes, aiming to discuss recent overnight incidents.
The alternative option is to install SentinelOps using a single Helm command, with the command available in the comments.
The developer does not request a GitHub star, but rather values feedback and opinions on the project. The project can be accessed at https://github.com/maxuver/sentinelops.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
