OpenMed (@OpenMed_AI) header
OpenMed (@OpenMed_AI) profile picture

Open-source AI for healthcare. 2,000+ Apache-2.0 clinical models. 600+ MLX and 700+ ONNX variants. Built for local and on-device AI. Free, forever.

Joined August 2025
Fine-tuned from @fastinoAI's GLiNER2.5 Small on 1,000 MedMentions abstracts, with three labels. Lab procedures are its weak spot, F1 28.9, about one in four found. It also missed "maintenance hemodialysis" in the card's last line. Not yet tested on hospital notes.
63
10 people sent their first pull request to OpenMed during 3.3, and that makes us so happy!! 118 pull requests in ten days, 25 of them from 14 community contributors. Every name is on the card. Good first issues are open if you want yours on the next one.
1
8
501
We tried to skip the review ten different ways. OpenMed 3.3 refused all ten. Export before the drug name was confirmed, reuse an old sign-off after a correction, write FHIR from an unreviewed draft. Each came back with a reason. Only the reviewed note became FHIR R4.
1
14
746
The discharge summary looked clean. The patient's name was still inside, in white text, hidden text and a comment. We hid a synthetic name in five files like that. OpenMed 3.3 found it in all five. Two came out redacted, two exports were stopped and one PDF was rejected.
1
10
678
We dictated a synthetic patient's name, birth date and phone number to OpenMed 3.3, fully offline. All three came back masked before a single line of transcript was released. Three words it wasn't sure about, metoprolol, mg and a 2, wait for a person to confirm.
1
5
500
A clinic visit is a conversation, a scanned form, an ECG and an image. OpenMed 3.3 handles all four, locally. Visit audio becomes a transcript screened for identifiers, then a FHIR draft a clinician reviews. Hidden text in a PDF is caught before export. Out now, Apache-2.0.
3
3
56
2,416
Fine-tuned from @fastinoAI's GLiNER2.5 Small on 1,000 MedMentions abstracts. It now finds 655 of 987 labeled mentions, up from 333, with 476 wrong tags instead of 1,270. One label covers organs, tissues, cells and body fluids. Not yet tested on hospital notes.
3
5
167
Fine-tuned from @fastinoAI's GLiNER2.5 Small on 800 MedMentions abstracts, then scored once on 200 others: F1 45.1 to 67.4. It finds the drug, not the dose, and it counts enzymes and receptors as chemicals. The card has 10 real outputs and its limits.
2
5
166
Fine-tuned from mmBERT, the multilingual encoder from @jhuclsp. One sentence is not a benchmark: on the 150 held-out documents GLiNER2.5 is still ahead, 73.3 F1 to 70.0, because it is more precise. pip install -U "openmed[hf]"
177
A draft discharge brief says potassium stayed normal. The cited note says 6.1 mmol/L on admission. OpenMed 3.1 checks every claim against reviewed evidence with a local NLI model, nli-deberta-v3-small. One contradiction: no brief. Fixed draft: 5 of 5 pass, sent for review.
1
6
597