maziyarpanahi/openmed
Local-first healthcare AI: clinical NER & HIPAA PII de-identification that runs 100% on-device. 2,200+ medical models, 21 languages, Apple MLX + Python, no cloud, no patient data leaving your network. Apache-2.0 observed · 2026-08-28
Health v2 · maintenance only
83/100
- Activity 99
- Release rhythm 98
- Longevity 23
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.
- gap_med: 7
- age_days: 333
- days_rel: 12
- days_push: 7
- n_releases_24m: 42
Adoption not part of the score
5166 stars · 650 forks observed · 2026-08-28
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded
OpenMed is a local-first healthcare AI SDK for clinical named-entity recognition and HIPAA PII/PHI de-identification that runs entirely on-device with no cloud dependency. It ships 2,000+ Apache-2.0 medical models across 35 languages, with runtimes for Python, Apple MLX/CoreML (Swift), Android ONNX, and browser Transformers.js.
Use cases
- de-identify patient notes for HIPAA compliance without sending data to a cloud API
- extract clinical entities like medications, diseases, and anatomy from medical text
- redact names, MRNs, phone numbers, and SSNs from clinical documents
- run medical NER models on an iPhone or iPad with Apple MLX
- run PII detection in the browser with Transformers.js
- deploy clinical NLP on-premise in a hospital network
- convert HuggingFace medical models to ONNX for mobile inference
When to choose
- you need HIPAA-compliant PHI de-identification where patient data must never leave the device or network
- you want on-device clinical NER across many languages with pre-trained medical models
- you build iOS, Android, or browser apps that need local medical text processing
- you need an on-premise alternative to cloud clinical NLP vendors
When to avoid
- you need general-purpose (non-medical) NER or PII detection with broader domain coverage
- you want a fully managed cloud service with no local model management
- you need generative clinical LLM features rather than token classification and de-identification
- your target platform is unsupported by the MLX, CoreML, or ONNX runtimes
Facets
library · maturity active
nlp machine-learning llm-inference security privacy ocr pdf sdk healthcare privacy machine-learning self-hosted python browser cross-platform wasm self-hosted clinical-nlp ner pii-deidentification hipaa on-device-ai apple-mlx healthcare-ai sovereign-ai on-premise multilingual natural-language-processing localization macos ios android swift
8 sources
- readme: https://github.com/maziyarpanahi/openmed · fetched 2026-08-28 · 7223105682de
- homepage: https://openmed.life/ · fetched 2026-08-29 · 3513df2915bb
- site_page: https://openmed.life/docs · fetched 2026-08-29 · 79112b647c39
- site_page: https://openmed.life/docs/api-reference · fetched 2026-08-29 · fcb99ca7f761
- site_page: https://openmed.life/docs/mlx-backend · fetched 2026-08-29 · 4acec1810fa5
- site_page: https://openmed.life/docs/swift-openmedkit · fetched 2026-08-29 · ed914fc86c7d
- site_page: https://openmed.life/docs/export-transformersjs · fetched 2026-08-29 · 00e6f1fcadbf
- site_page: https://openmed.life/docs/export-onnx-android · fetched 2026-08-29 · 78851ffa47f8
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| maziyarpanahi/openmed | main | 83 |
For agents
markdown · JSON · MCP: product_card(name="maziyarpanahi/openmed")
Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem