Sentinel
- 4 Devlogs
- 18 Total hours
It's an AI Infrastructure Engineer which manages VPS while you sleep :]
Ship #1
Pending review
I built Sentinel, a self-hosted AI infrastructure engineer for a Linux server.
Sentinel continuously monitors a server, detects incidents such as crashed containers, stopped services, high memory usage, and high load, then follows an Observe → Diagnose → Plan → Act → Verify loop. It can investigate the problem, propose an exact fix, wait for my approval, execute the fix through a restricted root agent, and then verify that the problem actually recovered.
The most challenging part was making the AI useful without giving it a shell. Sentinel is split into two privilege boundaries: the main web application has no server access, while a separate root agent exposes only 27 named tools with fixed risk levels. Every action is checked again by the agent, and anything that changes the server requires approval. There is deliberately no arbitrary command execution.
I’m especially proud that this is not just an AI demo. It is a real, production-running system with a live dashboard, incident history, deployments and rollbacks, container/service management, Discord/Slack approval, Ask Sentinel for natural-language read-only diagnostics, encrypted API keys, an installer, CLI, database migrations, and tests that guard against shell execution. It runs in under 120 MB RAM, uses under 2% CPU while idle, and starts in under 2 seconds.
To test it: open the demo URL, explore the dashboard, incidents, and Ask Sentinel interface. The demo is designed so it can be explored without access to my actual server. For the full project, the source code and setup instructions are available in the public repository.
The biggest idea behind Sentinel is simple: AI should be able to help operate real infrastructure without being handed unrestricted control of it.
.jpg)
9h 54m 57s logged
DEVLOG_5: Added Ask Sentinel and Incident tracking feature. along with a lot of other micro features. The way Incident tracking works is quite smart:
the backend services (very lightweight) actively searches for any kind of error affecting the VPS. It then loges an incident and sends me a msg via discord webhook. I can approve the incident and then Sentinel will collect information like what as the problem the possible areas affected and stuff like that and after the report is compiled it is sent to the AI model of your choice which then generates an AI diagnosis and a list of process to fix the problem.
3h 1m 12s logged
DEVLOG_3: Added this specific hardware stats page where the real time data related to the CPU and Memory is displayed.
4h 3m 28s logged
DEVLOG_2: Initially Sentinel was just a view only dashboard to see some stats of my VPS, but now I am working on a AI chat system as well called “Ask Sentinel”
46m 26s logged
DEVLOG_1: I recently made a home server using my 7 year old laptop!! And now I am planning to develop an AI assisted dashboard for it which will help me manage my server remotely. Any suggestions will be appreciated :]
