openmed
Local-first SDK for clinical extraction and de-identification workflows on hardware you control.
Decision gist · record as of 2026-08-14
Yes, if you need local clinical text extraction and de-identification and can validate model terms for your deployment. Low install friction, active maintenance, permissive license, and no known vulnerabilities. Requires upfront work to acquire and validate model artifacts and confirm clinical fitness for your use case—this is not a plug-and-play compliance tool.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10+.
- Model artifacts must be available before analyze_text() is called; the package does not bundle them—you must download or configure them separately.
- Low friction: pure Python wheel with four runtime dependencies (faker, jieba, pysbd, pyyaml).
License · maintenance · safety
Apache-2.0 (permissive) — Apache-2.0 permissive license on the SDK source itself. Model and dataset terms vary separately; deployment owners must validate each model's license, privacy behavior, and clinical fitness for their use case.
last release 2026-08-12 (2 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 3,975,274 downloads/mo, #2,432 on PyPI
Alternatives
Verify before relying
pip install openmed
from openmed import analyze_text
result = analyze_text(
"Patient started on imatinib for chronic myeloid leukemia.",
model_name="disease_detection_superclinical",
)
for entity in result.entities:
print(f"{entity.label} {entity.text} {entity.confidence}")- Whether model artifacts are bundled with the package or must be downloaded separately on first use
- Actual latency and throughput for typical clinical documents on standard CPU hardware
- Whether the package alone achieves HIPAA compliance or requires additional deployment configuration
- Whether all 33 supported languages are available in the base package or require separate model downloads
What it is and what it does
OpenMed is a local-first Python SDK for clinical text processing: it extracts medical entities (diseases, drugs, procedures) and detects personally identifiable information (names, addresses, IDs, billing data), then returns de-identified text. The core runtime runs on your hardware after required model artifacts are available; model downloads, remote adapters, and user-configured integrations may use the network. It depends on faker, jieba, pysbd, and pyyaml for text processing and data generation.
The package targets Python 3.10+ and ships as a pure wheel. It supports multiple deployment surfaces—Python, Swift/MLX on Apple Silicon, Android/ONNX Runtime Mobile, and browser/Transformers.js—though the PyPI package itself is the Python runtime. Deployment owners are responsible for validating each model's terms, privacy behavior, and clinical fitness; using the SDK does not itself establish HIPAA compliance.
Use it for
- De-identify clinical discharge notes or EHR text before sharing with research teams or external systems
- Extract structured medical entities (diagnoses, medications, procedures) from unstructured clinical narratives
- Build a local clinical NLP pipeline that never sends patient data to a cloud API
- Integrate clinical text processing into healthcare applications on Apple Silicon or Android devices
- Validate and redact PII from synthetic or real clinical documents for compliance workflows
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you need local clinical text extraction and de-identification and can validate model terms for your deployment.
Low install friction, active maintenance, permissive license, and no known vulnerabilities. Requires upfront work to acquire and validate model artifacts and confirm clinical fitness for your use case—this is not a plug-and-play compliance tool.
Install
openmed on PyPI
Before you install
Low friction: pure Python wheel with four runtime dependencies (faker, jieba, pysbd, pyyaml). Active maintenance—released 2 days ago. Requires Python 3.10+.
Requires Python 3.10+. Model artifacts must be available before analyze_text() is called; the package does not bundle them—you must download or configure them separately.
License in practice
Apache-2.0 permissive license on the SDK source itself. Model and dataset terms vary separately; deployment owners must validate each model's license, privacy behavior, and clinical fitness for their use case.
Quickstart
pip install openmed
from openmed import analyze_text
result = analyze_text(
"Patient started on imatinib for chronic myeloid leukemia.",
model_name="disease_detection_superclinical",
)
for entity in result.entities:
print(f"{entity.label} {entity.text} {entity.confidence}")Verify before relying
- Whether model artifacts are bundled with the package or must be downloaded separately on first use
- Actual latency and throughput for typical clinical documents on standard CPU hardware
- Whether the package alone achieves HIPAA compliance or requires additional deployment configuration
- Whether all 33 supported languages are available in the base package or require separate model downloads
Package facts
| License | Apache-2.0 permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 4 packagesfakerjiebapysbdpyyaml |
| Maintenance | Actively maintained 2 days since the last release |
| First released | |
| Downloads | 3,975,274 / month, #2,432 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
Evidence: openmed-2.1.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “clinical text extraction”
- openmedExtracts medical entities and personally identifiable information…
- negspacyAdds negation detection to spaCy pipelines using the NegEx algorithm,…
- PyRuSHPyRuSH segments clinical and telegraphic text into sentences using…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also carelytics · gliner2 · presidio-image-redactor · presidio-analyzer · argus-redact · gliner · hl7 · emrvalidator · simple-icd-10-cm · icd-mappings