DOCS — OVERVIEW · DOCS HOME
OpenMed Agent documentation¶
Terminal-native AI for clinical workflows. Install the agent, choose a lane, and keep every plan, tool call, and artifact inspectable.
Start here¶
OVERVIEW
Getting Started →
Install, authenticate, choose a lane, and run the first workflow.
PRODUCT
CLI Reference →
Commands, agent modes, flags, and workflow-facing behavior.
PRODUCT
Agent TUI →
The terminal interface, plans, sessions, and keyboard flows.
PRODUCT
Skills →
The built-in skill library and how to add your own local skills.
PRODUCT
Profiles →
Built-in config presets and how they affect current settings.
PRODUCT
Configuration →
Files, directories, runtime settings, and environment variables.
INTEGRATIONS
MCP Connectors →
Add remote MCP servers and expose them as namespaced tools.
INTEGRATIONS
Native Medical Services →
How extraction, de-id, terminology, RxNorm, and HCC endpoints deploy.
TRUST
Privacy & Security →
Runtime boundaries, PHI mode meaning, token storage, network paths.
TRUST
Audit Trail →
Private run traces in Hugging Face datasets, buckets, or local storage.
The system at a glance¶
OpenMed separates the operator runtime, the model-provider path, and the medical service tier — visible, configurable, and suited to sensitive or high-volume clinical processing.
PLANE 01 · LOCAL
Operator runtime
Sessions, plans, tool traces, provenance, and workflow artifacts stay on the machine running OpenMed.
operator-controlledvisible-review
PLANE 02 · PROTECTED
Clinical extraction & de-identification
NER, PII detection, and de-identification run through a dedicated native service endpoint.
protected-extractionPII-aware
PLANE 03 · PROTECTED
Terminology, coding & HCC
Semantic search, validation, crosswalks, drug safety, risk adjustment, and comorbidity scoring across 16 clinical datasets.
terminologyopenFDAHCC V28 / RxHCC
See Native Medical Services for the deployment story, and the product page for dataset coverage numbers.