Skip to main content

OpenMed Agent

AI-powered medical assistant with interactive TUI, agentic workflows, and remote NLP inference

OpenMed Agent provides an intelligent terminal interface for clinical workflows — entity extraction, PII de-identification, and medical reasoning — powered by LLMs and remote NLP inference.

License Python 3.10+


Quick Start

Installation

# Recommended: install the latest binary release
curl -fsSL https://github.com/openmed-labs/openmed-agent/releases/latest/download/install.sh | bash

# Install a pinned binary release
VERSION=0.0.1
curl -fsSL "https://github.com/openmed-labs/openmed-agent/releases/download/v${VERSION}/install.sh" | bash -s -- "${VERSION}"

Python Installation

# Install with TUI support
pip install openmed-agent[tui]

# Or install everything
pip install openmed-agent[all]

Launch the Agent TUI

openmed            # Launch interactive agent TUI
openmed agent      # Explicit agent command

Authenticate (for Codex models)

openmed login      # OAuth flow for Codex authentication

Features

  • Interactive Agent TUI — Rich terminal interface for clinical analysis and medical reasoning
  • Remote NLP Inference — NER and PII tools connect to remote inference endpoints via Docker
  • MCP Server Integration — Connect to medical data sources (PubMed, ICD-10, NPI, CMS)
  • Agentic Workflows — Plan-based execution with skill-driven task automation
  • Configuration Profiles — dev/prod/test/fast presets with flexible overrides
  • PHI Handling Modes — full, deid, strict modes for HIPAA-aware workflows

CLI Commands

openmed                    # Launch agent TUI (default)
openmed agent              # Launch agent TUI with options
openmed config show        # Show current configuration
openmed config profiles    # List available profiles
openmed mcp list           # List MCP server configuration
openmed mcp enable         # Enable MCP servers
openmed mcp doctor         # Check MCP server connectivity
openmed login              # Authenticate via OAuth
openmed oauth status       # Check authentication status

Remote Inference

NER and PII tools require a remote inference endpoint. Set the environment variable:

export OPENMED_INFERENCE_URL=http://localhost:8000

See services/inference/ for the Docker-based inference server.


Binary Releases

Standalone release archives are built by binary-release.yml and published with:

  • platform tarballs such as openmed-0.0.1-darwin-arm64.tar.gz
  • openmed-manifest.json for install.sh
  • openmed-checksums.txt for manual verification

To build a release artifact locally:

uv sync --extra all --extra build
uv run --no-sync python scripts/release/build_binary.py

Contributing

We welcome contributions! Whether it's bug reports, feature requests, or pull requests.


License

OpenMed is released under the Apache-2.0 License.


Citation

If you use OpenMed in your research, please cite:

@misc{panahi2025openmedneropensourcedomainadapted,
      title={OpenMed NER: Open-Source, Domain-Adapted State-of-the-Art Transformers for Biomedical NER Across 12 Public Datasets},
      author={Maziyar Panahi},
      year={2025},
      eprint={2508.01630},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2508.01630},
}

Metadata

Release files for openmed-agent 0.0.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for openmed-agent 0.0.1
File Size Uploaded Provenance Actions
openmed_agent-0.0.1.tar.gz 258.3 kB Without provenance Details for openmed_agent-0.0.1.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for openmed-agent 0.0.1
File Interpreter ABI Platform Actions
openmed_agent-0.0.1-py3-none-any.whl Python 3 none any Details for openmed_agent-0.0.1-py3-none-any.whl

Total release size: 579.0 kB

Release files / openmed_agent-0.0.1.tar.gz

Download URL openmed_agent-0.0.1.tar.gz
Size 258.3 kB
Tags Source
SHA-256 checksum
How to use checksums
d771085b65394411da6f7dea58c2aca94d9c4b7a4f77e00a2f22159dc38c367f
BLAKE2b-256 checksum
How to use checksums
ecf79ca343cf9b7fcb6521f119c837ef398544cb7de1c270434d7735868791ea
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.8

Release files / openmed_agent-0.0.1-py3-none-any.whl

Download URL openmed_agent-0.0.1-py3-none-any.whl
Size 320.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
b64c3d5e3cbbc2998493203fe9f200e1829f135aa582822b42355ddf8c45014a
BLAKE2b-256 checksum
How to use checksums
ffffbe55a33fe55bb660125069ee1e7f8ea8239e27c5fdd5060fbe677b1e8a9f
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.8

Security for openmed-agent 0.0.1

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.0.1 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page