Find tools › Open-source projects › Automate busywork

StartLux-Prism

Open-source project · by StartLuxLabs

Runs fast decision-making AI models directly on your own computer's graphics card without changing the original files.

Some setup

What it costs

Free and open source; you may pay for the AI model it uses.

Use it to

  • Classify customer support tickets into teams and urgency levels
  • Answer multiple structured decision questions from text or video
  • Serve decision models across single or multiple graphics cards

How to start

  1. Clone the repository and install dependencies: pip install -r requirements.txt

  2. Download the StartLux-Decision GGUF and configuration files from Hugging Face.

  3. Launch the server: python -m startlux_prism.server --gguf <file.gguf> --model-dir <dir> --port 8092

  4. Send classification questions via curl to receive calibrated probabilities.

Good to know. Requires Ampere or newer NVIDIA GPUs on Linux with CUDA drivers, has no built-in web authentication, and the model weights carry a non-commercial CC BY-NC 4.0 license.

Before you install

  • Found automaticallyNot reviewed by a person yet. Check it before installing.
  • Last updated 2026-10-27

More detail

An inference engine that serves StartLux-Decision GGUF models on NVIDIA GPUs behind a TypeSafe classification endpoint.

It delivers faster speeds and exact integer calculations compared to vLLM when scoring decisions. Reach for it when you want low-latency, repeatable probability readouts from text or video on your own hardware.

Similar tools

Descriptions are written in plain English from each project's own documentation and refreshed by our agent; this one was last checked 2026-10-23. Spotted a mistake? · Open in Find tools · © 2026 Which AI Map