79 pattern entries loaded locally. Your conversation is saved in this browser and restored on reload. In cloud mode, only your chat messages and API key are sent to the model provider; a local (WebGPU) model sends nothing to any AI provider. Clear it any time with New Session.
⚠ Experimental: This clinic is a research preview. Its diagnostic output is exploratory and has not been clinically validated. Do not rely on it for consequential decisions about AI systems without independent verification.
Session settings
This is a research preview. The 79 pattern entries are loaded locally in your browser.
If you choose a cloud model, your chat messages and API key go only to Anthropic's servers. Key is stored in this browser tab's memory (sessionStorage) and cleared on close. Your conversation transcript is also saved locally in this browser (localStorage) so it can be restored on reload; clear it any time with New Session, or by clearing this site's data.
If you choose a local (WebGPU) model, your chat messages stay on your device and are not sent to any AI provider. The model weights and the semantic-search encoder are downloaded once from CDNs (the MLC HuggingFace mirror, jsDelivr, and GitHub, which hosts the model runtime library) and cached in your browser; those CDNs see your IP address but none of your conversation. No API key needed.
Research preview — not for clinical use. All 79 pattern entries should be treated as working research instruments. The full axis 10 (entries 10.1–10.15), including the Hybrid Pathologies 10.4–10.15, was ratified into the canonical taxonomy in June 2026; the hybrids' detailed clinical write-ups are still maturing. Diagnostic output from this tool does not constitute expert clinical opinion.
An API key is required to start a cloud session. Paste your key above, or choose a local model.
Get one at console.anthropic.com. The key stays in this tab's memory and is cleared on close.
Cloud models require an API key. The local model (Qwen 3 8B) needs none; the first run downloads its weights (~5 GB). Running it needs more memory than the download alone: the 32k context window adds a multi-gigabyte KV cache, so it needs roughly 8–10 GB of GPU or unified memory in total. Its memory floor is shown when you select it.
Start a new session?
This will clear the current conversation and provenance trail.