Questions, answered
What metahub is, what it makes, and what it costs. Questions about installing from the catalog, updating what you installed, or publishing into it are answered in the registry FAQ.
What is metahub?
metahub builds open infrastructure for AI tools. The registry is a public catalog of skills, MCP servers, agents, and plugins that install into any AI coding editor with one command, and nothing is listed there until it has been evaluated. Around it sit a free observability dashboard for the people who publish those tools and Assay, the open evaluation framework the listings are scored with. Browsing, installing, and publishing are all free.
What does metahub actually make?
Four pieces that fit together. The registry at registry.metahub.ai is the public catalog you install from. The publisher dashboard at developer.metahub.ai is where you point metahub at a GitHub repository and get a listing plus live usage data for it. Assay is the open-source framework every listing is evaluated with. And the mh CLI and the metahub MCP server are how artifacts reach your editor, whether you work in a terminal or ask your assistant in plain language.
What does metahub cost?
Nothing. Browsing the catalog, installing artifacts, publishing your own, and the observability dashboard that comes with publishing are all free, there is no paid tier, and metahub takes no cut of anything you publish. Publishing transfers no rights either: your code stays in your own repository under your own license, and the listing links to it rather than hosting it.
Is Assay open source, and can I run it in my own CI?
Yes. Assay is released under Apache-2.0 and published on npm, so you can run the same evaluation locally or in your CI pipeline that metahub runs before listing. Because the checks and scoring are open, you can see exactly why an artifact scored what it did, and open a pull request when you think a check is wrong.
What usage data does metahub give publishers?
Publishers see invocations over time, p50 and p95 latency, error rate, which models and tools the artifact was used with, and recent errors. The data comes from an opt-out telemetry SDK that reports anonymous usage. It never sends prompts, file contents, or any user data, and end users can switch it off.
Where should I start?
If you want to use AI tools, start at registry.metahub.ai: browse or search the catalog, read the public evaluation report on anything that looks useful, and install it with one command. If you have built something you want other people to find, sign in with GitHub at developer.metahub.ai and point metahub at the public repository. Neither path asks for a card, and the registry's own FAQ covers the install and publishing mechanics in more detail.