Ross ROSS = Recommend OSS · open-source software intelligence for agents

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

github.com/maziyarpanahi/openmed · homepage · Python · Apache-2.0 (permissive) 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

Full methodology

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

Member repositories

RepositoryRoleHealth v2
maziyarpanahi/openmedmain83

For agents

markdown · JSON · MCP: product_card(name="maziyarpanahi/openmed")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem