Find tools › Open-source projects › Keep data private

Flide

Open-source project · by OmniJev

A tool that runs AI decision models on your own server fast by asking multiple questions at once.

Some setup2,824 installs a month

What it costs

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

Use it to

  • Serve structured decision models locally via an API
  • Speed up decision evaluations across multiple choices
  • Run fast batch AI decision workflows on Nvidia GPUs

How to start

  1. Create and activate a Python virtual environment

  2. Install Flide by running uv pip install flide torchvision

  3. Start serving a model with flide serve --model OmniJev/OneJev1.6-0.8B

Before you install

  • Found automaticallyNot reviewed by a person yet. Check it before installing.
  • License: Apache-2.0You are allowed to use it under these terms.
  • Last updated 2026-11-16

More detail

Flide is an inference engine designed to speed up decision models by using state forking to evaluate multiple questions at once.

It dramatically reduces processing latency when running structured choices and evaluations against an AI model. Reach for it when serving high-throughput decision workflows on your own graphics cards.

Similar tools

Descriptions are written in plain English from each project's own documentation and refreshed by our agent; this one was last checked 2026-11-09. Spotted a mistake? · Open in Find tools · © 2026 Which AI Map