Llama-monitor Maps System Health for Local AI Models

Llama-monitor provides a web-based control panel for running and tracking local large language model servers in real time. This lightweight utility tracks hardware performance, manages configuration files, and keeps system resources visible without relying on extra software.

Developed by Arte-fact, the tool replaces manual terminal commands and scattered log files with a single interface that adapts to different computer setups. It handles routine tasks like starting programs and tracking memory use, which reduces setup friction for everyday workflows.

Core dashboard functions

• Start and stop language model servers directly from saved templates.
• Track GPU temperature, memory usage, clock speeds, and power draw for AMD and Nvidia hardware.
• Watch prompt speed, text generation rates, and active memory windows.
• Save and edit configuration templates that survive computer restarts.
• Browse local folders to locate model files and server programs.
• Interact with running models through a built-in chat window.
• Install as a standalone application on desktop or mobile devices.

Operators managing daily experiments benefit from combining server controls into a single window. This setup removes the need to switch between command terminals while adjusting settings for different projects.

Development notes

The creator initially built the software around one specific machine, which required a full rewrite to support diverse hardware layouts before public release. Written in Rust, the program bundles into a single file that skips extra setup tools and packs the interface directly into the executable.

"Feel free to PR improvements if needed,"

the creator noted in a community post. Users with custom folder structures should manually verify that their system recognizes standard monitoring commands, since the dashboard depends on those tools for automatic detection.

Explore the full source code and setup instructions on GitHub.