Find tools › Open-source projects › Keep data private

NeoHorse

Open-source project · by TokenRhythm

Run open-weight AI models locally for agent tasks and structured decision-making.

Some setupWell known

What it costs

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

Use it to

  • Run local 4B or 9B agent models
  • Make structured application decisions with Jev
  • Execute tool-use and coding workflows

How to start

  1. Download the model weights from Hugging Face or ModelScope.

  2. Set up your local inference environment using compatible frameworks.

  3. Load the model using standard text generation pipelines.

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 2026-09-26

More detail

NeoHorse is a family of open-weight language models and decision models designed for agent workflows, tool use, and structured routing.

Developers looking to run specialized open-weight models for agent routing and decision-making on their own hardware can use NeoHorse for local inference.

Similar tools

Descriptions are written in plain English from each project's own documentation and refreshed by our agent; this one was last checked 2026-09-29. Spotted a mistake? · Open in Find tools · © 2026 Which AI Map