# Created with WinGet Releaser using komac v2.16.0
# yaml-language-server: $schema=https://aka.ms/winget-manifest.defaultLocale.1.12.0.schema.json

PackageIdentifier: eladser.mtop
PackageVersion: 1.3.0
PackageLocale: en-US
Publisher: Elad Sertshuk
PublisherUrl: https://github.com/eladser
PublisherSupportUrl: https://github.com/eladser/mtop/issues
PackageName: mtop
PackageUrl: https://github.com/eladser/mtop
License: MIT
LicenseUrl: https://github.com/eladser/mtop/blob/HEAD/LICENSE
ShortDescription: htop for your local AI
Description: A terminal dashboard for local AI servers (Ollama, llama.cpp, LM Studio, vLLM). Shows loaded models and their VRAM, the GPU, and every request with its tok/s. Unloads models that overstay.
Tags:
- gpu
- llamacpp
- local-llm
- ollama
- tui
ReleaseNotes: |-
  Watch more than one box, see more per request, and a couple of new numbers.
  - Multi-host: give -ollama a comma list and mtop stacks the models and GPUs from each machine, tagged by host. Handy if you run models on a couple of boxes.
  - GPU util and memory now draw as sparklines over time, next to the live numbers.
  - Request inspector: run with -inspect, press i, and you get the last request's prompt, completion, and a load/prompt/decode timing split. Off by default; the text it captures is stripped of control bytes so a model can't smuggle escape sequences into your terminal.
  - Session energy on the TOK/S line: watt-hours used and tokens per watt-hour. It's whole-GPU power, so read it as a rough efficiency number.
  - compare -openai <url> runs the comparison against llama.cpp, LM Studio or vLLM, not just ollama.
  - -mem-alert and -temp-alert to set the alert thresholds instead of the built-in 93% and 87C.
  brew and scoop pick this up as usual; winget follows once Microsoft merges the bump.
ReleaseNotesUrl: https://github.com/eladser/mtop/releases/tag/v1.3.0
ManifestType: defaultLocale
ManifestVersion: 1.12.0