LM Studio today
LM Studio is a local runtime on the AI Stats roadmap. The importer accepts no LM Studio files, this page is excluded from search indexing, and no date is promised.
Planned integration
LM Studio adapter plan
Locally stored conversations from the desktop application.
What the adapter would read
Locally stored conversations from the desktop application.
What it could measure
Precise token counts and model names, because everything runs on your own hardware and nothing is rate-limited away.
What has to be true first
Local runtimes report tokens precisely and timing loosely. The metric quality labels for this source would look very different from a hosted provider, and that difference has to be visible rather than smoothed over.
Privacy, unchanged
When it ships it will follow the same stats-only rule as every supported adapter: parsing happens in your browser, and raw prompts, responses, attachments, and local paths never reach the server.
In the meantime
Import from one of the seven supported providers instead. If this source matters to your workflow, saying so through the contact page is the strongest signal available for ordering the queue.