MLX Harmony: Experimental Archive

Run GPT-OSS and other MLX-compatible models through a single, lightweight interface.

View on GitHub

MLX Harmony was a short experiment in MLX engines, GPT-OSS, and the Harmony prompting structure. I am retaining this page as a record of that work, but I am not developing it as a product or using it as the model-hosting layer.

My current model-engineering work has moved to MLX Forge, where I am concentrating on model conversion, inference performance, and the measurements needed to tell whether an optimization actually helps. That repository remains private while I work through its early milestones.

Support This Work

If you enjoyed this article or found it useful, please consider supporting my work. Contributions help fund the time, infrastructure, and independent development behind the articles, tools, and research on this site.

Join the Discussion

Comments for this post live in GitHub Discussions. That keeps moderation in one place and gives the conversation a stable home.

Join Our Mission

Join Distributed Thinking Systems in local-first AI, secure automation, sensitive workflow analysis, and developer tooling work.

Community Collaboration: Contribute data, provide expertise, test tools, or participate in applied AI and open-source projects.
Professional Services: Get help with local AI setup, secure automation, developer infrastructure, or Unix/Linux/macOS systems engineering.

Supporting the work helps keep practical tools, research, and resources available to people handling sensitive data and difficult workflows.

Get In Touch

If you want to talk privately about local AI, secure automation, sensitive workflow analysis, systems engineering, collaboration, or a specific problem, use the contact page.

If you would rather keep it public, join the wider conversation on GitHub Discussions.

The site is small by design, so the shortest path is usually best: private inquiries through the form, public discussion through GitHub.