<2-3 sentences summarising what the project addresses and solves, the target audience, and the benefit.> This command-line interface (CLI) utility is designed to simplify the process of obtaining direct download links for Ollama models and automating their local installation. It serves developers, researchers, and enthusiasts working with Ollama, offering an efficient solution for managing model acquisition and deployment.

How It Works

Written in Golang, the tool utilizes the Requests library to fetch necessary download links. It functions as a CLI application that can either generate direct download URLs for specified Ollama models or install locally available model files by copying them to Ollama's designated model directory. This approach bypasses standard Ollama pull mechanisms for direct file management.

Quick Start & Requirements

• Installation: Download the pre-compiled binary files from the project's Release page, ensuring compatibility with your specific operating system and processor architecture.
• Usage:
  • To generate direct download links for a model: Execute omdd get <model-name>:<tag> (e.g., omdd get deepseek-coder-v2:latest). The tool will then fetch and display the download URLs.
  • To install locally available Ollama models: Run omdd install --model=<model-name> --blobsPath=<downloaded-blobs-path>. This command requires a manifest file to be present in the specified <downloaded-blobs-path>.
• Prerequisites: Requires downloading the appropriate OS and architecture-specific binary.
• Links: Direct links to binaries are available on the project's Release page.

Highlighted Details

• Enables the generation of direct, shareable download links for any Ollama model.
• Automates the installation of Ollama models from local files, streamlining deployment.
• Offers robust proxy support, including HTTP/HTTPS and SOCKS5 protocols, configurable via standard environment variables, and accommodates authenticated proxy setups.

Maintenance & Community

The provided README does not contain specific details regarding notable contributors, community support channels (such as Discord or Slack), project roadmaps, or any information about sponsorships or partnerships.

Licensing & Compatibility

The project is distributed under the permissive MIT License. This license generally allows for broad usage, including integration into commercial and closed-source applications, without significant restrictions.

Limitations & Caveats

A significant caveat is that the tool does not perform any checksum validation on downloaded model files; users are strongly advised to verify file integrity manually. Furthermore, the model installation process may appear unresponsive or frozen for extended periods, requiring user patience.