A server for Apple Silicon Macs that loads local models from a folder and answers over HTTP with an OpenAI-style API and an Anthropic Messages endpoint.
Our description, from the project's README, as of 2026-10-21.
Runs onThe places the vendor's own pages say the product runs: your machine, a container environment you run, or a cloud service the vendor runs. It is not a limit.
Models runWhere the vendor's own pages say the product's models run, not a limit: your machine, a container environment you run, the model company's cloud (servers of the company that makes or serves the model), or a cloud provider's model service. For a cloud, read the data and compliance lines of the company running it, linked by its name.
Compliance: Set by whoever runs itThe answer belongs to whoever runs the software, because open-source software has no maker running it for you., for their own deployment.
Data: Set by whoever runs itThe answer belongs to whoever runs the software, because open-source software has no maker running it for you., with telemetry not checked yetWe have not read a page of the right kind for this question yet..
Model and where it runs: Run by its operator.
Details: What the project's own pages state, not a compliance determination.
What the maker's own pages said on the dates shown, not a compliance determination.
GitHub page: omlx(the product's own site, from our list of products; not read for these lines)
The readings behind this page
Our summary of the vendor's pages as of the dates shown on each line (2026-10-21 to 2026-10-24); confirm on the vendor's page.
Claude Code with a local server
The oMLX README lists a POST /v1/messages endpoint described as the Anthropic Messages API, next to OpenAI-style endpoints on the same server. (github.com page, read 2026-10-21)Caveat: The Claude Code gateway page says Anthropic provides no support when a gateway sends Claude Code's requests to models that are not Claude (code.claude.com page, read 2026-10-21).
What a local model must meet
In oMLX's README install section, directly after the from-source steps, the page says oMLX requires macOS 15.0 or later (Sequoia), Python 3.11 to 3.13 and an Apple silicon chip (M1 through M5). (github.com page, read 2026-10-21)
About the product
oMLX's README describes oMLX as LLM inference optimized for the user's Mac. (github.com page, read 2026-10-24)
oMLX's README says its caching is meant to make locally run LLMs usable for real coding tasks, with tools like Claude Code. (github.com page, read 2026-10-24)
Our reading of vendors' pages, as of the dates shown. Confirm on the vendor's page before relying on any line that cites it. To report an error write to report@crinaro.ai