I built an autonomous SRE system where a local LLM diagnoses production incidents, proposes a fix, and a deterministic engine decides whether that fix is ever allowed to run. The whole thing works inside your own network — zero data egress.
It's called Sentinel. It's a prototype and a learning project: I started from scratch on a Mac and used it to go deep on distributed systems, gRPC, local LLM inference, and safe automation. This post walks through why it's built the way it is — the design decisions are the interesting part.
Repo: https://github.com/Blazi2002/sentinel
The problem
Modern observability is passive. Prometheus and Grafana tell you that something is wrong, but a human still has to diagnose the cause and type the fix — often at 3 a.m.
