OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Local & Self-hosted AI

Mere Run

Mere Run is a Swift-based local AI runtime and command-line tool for running language models, generating media, analyzing images and geospatial data, training adapters, evaluating models, and executing workflow graphs. It also serves a loopback OpenAI-compatible API.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Mere Run — OpenViST project profile in Local & Self-hosted AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Mere Run when you want model-managed AI workflows on your own machine, especially from a CLI or a local application using its loopback OpenAI-compatible API.

Who it is for

  • Developers who want to run model-backed applications against a local OpenAI-compatible API.
  • Creators who want command-line access to local image, speech, music, sound and video workflows.
  • AI practitioners managing local models, adapters, evaluations or reusable workflow graphs.

Documented uses

  • Generate an image using an installed local model.
  • Run language-model chat or code tasks and other documented text workflows.
  • Create speech, music, sound and video through model-specific commands.
  • Analyze images or geospatial data, train adapters and evaluate models.
  • Serve a local OpenAI-compatible API or run a portable workflow graph.
Before you choose

Requirements & limits

The repository is public and specifies an MIT license. Apple Silicon macOS is the primary platform; headless Linux CUDA packages are also available.

  • Apple Silicon macOS is the stated primary platform; Linux support is described as headless CUDA packages.
  • Model size, memory requirements and licensing vary by model; the CLI documents a pull preflight and model catalog.
  • The iOS client connects to users’ machines and its image and chat inference is described as experimental on supported iPhones.
  • The macOS Studio app uses the same CLI, model store and run history.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Generate an image with a local model

Review the download plan, install the documented image model, and generate an image file.

Before you start

  • Install the Mere Run CLI using the repository’s installation instructions.
  • Review the selected model’s catalog entry for its size, memory requirements and license.

Steps

  1. Run mere.run model pull image-zimage-nano --preflight --json to inspect the download plan.

  2. Run mere.run model pull image-zimage-nano to download the model.

  3. Run mere.run image generate --model image-zimage-nano --prompt "a ceramic mug in soft morning light" --output ./mug.png.

Expected outcome

The command is documented to generate `mug.png` in the working directory.

Guide limitations

  • Model sizes, memory requirements and licenses vary; review the catalog entry and preflight before downloading.
  • Available inputs and controls depend on the selected model.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
sawfwair/mere-run · Official homepage title · retained in its source language
How we review sourcesSuggest a correction