Unverified50% confidenceFactExact time
OpenMedCheck uses the open-weights model Gemma running on the hospital's own GPUs, the app binds only to 127.0.0.1, the only external call is to the local model, and patient context is not logged, stored or cached.
1
Sources
50%
Confidence
Long-term
Relevance
10/18/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn the official direct-connection mode, Cursor integrates OpenAI model capabilities directly into the product, allowing users who subscribe to a Cursor plan to seamlessly use the GPT series of models without additional configuration.63% similarUnverifiedThe Gemma series is released in open-weight form, allowing developers to download model weights and run them locally or on private servers.63% similarUnverifiedOpenMedCheck uses a three-layer architecture: the first layer runs Gemma locally via Ollama to read free text and output strict JSON; the second layer is a non-AI program that verifies the model's answers (checking whether quotes appear in the source text, whether semantics match, whether it is negated, whether it concerns a relative, and whether an old event is treated as new); the third layer is a 25-rule if-then table that makes the final decision, of which 23 rules were reviewed by clinical experts and 2 past-history rules were added later and not reviewed.62% similarUnverifiedOpen source projects such as OpenTelemetry provide mature observability integration solutions for application-layer code, but stored procedures run inside the database engine, making their execution details nearly opaque to external tracing systems.61% similarUnverifiedIntegration can be achieved by pointing OpenClaw to http://localhost:11434/v1 and setting the model to qwen3.5:35b, with quantization, GPU offloading, and context management handled automatically by Ollama.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1064187API
curl https://kongchang.com/api/v1/knowledge/claims/1064187MCP
get_claim(id=1064187)