# MiaAI-Lab/sparkDash

> Real-time web dashboard for monitoring one or more NVIDIA DGX Spark (GB10) machines and other Linux GPU hosts: streams GPU, CPU, memory, network, local LLM, ComfyUI and Hermes Agent metrics over WebSocket.

- Magnitude: 2.0 out of 10 — Steady
- Stars: 548 total · +1 star measured 2026-10-07, 11:04–12:47 UTC, ≈ 6 by evening
- Star trust: star growth looks organic
- Category: DevOps & infrastructure · Language: JavaScript · License: MIT · Created: 2026-07-19 · Last push: 2026-10-06
- GitHub: https://github.com/MiaAI-Lab/sparkDash · Homepage: https://mia-ai.net · Page: https://gitnova.dev/en/r/MiaAI-Lab/sparkDash

## Useful for

- Watch GPU, unified memory and network load of several DGX Sparks in one browser window
- Benchmark decode and prefill tok/s of local LLM servers (llama.cpp, vLLM, SGLang) with built-in tools
- Add and reorder Spark hosts from the UI without restarting the service

## Why it’s here

- Star-counter measurements on 2026-10-07 (UTC), 11:04–12:47: 547 → 548 stars (+1). This is the change over that interval.
- Estimated end-of-day forecast: about +7 stars, using observed gains and the previous day.
- Over the last two days the pace is 2.6× that of the previous week and a half.
- GitHub Trending JavaScript today: #12, +22 stars.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 114
- Issues and pull requests: 172
- Watchers: 6
- Average over the last week: 6 per day
- Usual pace: 7 per day
- Stars in the last hour (measured): 0
- Latest release: media-showcase (2026-07-23)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-08 … 2026-10-07: 5, 5, 4, 8, 7, 10, 10, 6, 4, 7, 10, 4, 2, 2, 4, 2, 6, 9, 6, 4, 8, 16, 3, 4, 3, 1, 4, 3, 24, 1

## Spotted in now

- GitHub Trending JavaScript today: #12, +22 stars

## Similar by description

1. **MiaAI-Lab/GLM-5.3-Flash-EXL3-2x-DGX-Sparks-TensorFold** — 2.6 · Cooling · Language models · Shell · +7 stars measured 2026-10-07, 00:22–12:43 UTC, ≈ 13 by evening
   Scripts to serve GLM-5.3-Flash on two NVIDIA DGX Sparks via TensorFold with an OpenAI-compatible API, 1M-token context, and image/video input.
   Full card: https://gitnova.dev/en/r/MiaAI-Lab/GLM-5.3-Flash-EXL3-2x-DGX-Sparks-TensorFold.md
2. **RaysunKR/termirai** — 0.0 · Steady · DevOps & infrastructure · TypeScript · Not enough measurements today
   A self-hosted web console for remotely managing terminals across many Windows, Linux and macOS machines, with a built-in OpenAI-compatible AI agent that can run commands on one, several or all connected hosts.
   Full card: https://gitnova.dev/en/r/RaysunKR/termirai.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-07 12:58 UTC, updated every 30 minutes.