Nomad
Nomad connects AI agents to scientific foundation models (SciFMs). It serves PyTorch-backed scientific tools over the Model Context Protocol (MCP), and it can also expose MCP tools as typed Python callables inside a code-execution sandbox.
Documentation site | Getting started | Model builder guide | Reference
What Nomad does
- Serve SciFMs and regular Python tools over MCP with
nomad serve. - Load model artifacts from Hugging Face, local storage, or Git/Git LFS.
- Proxy MCP servers into a Python sandbox with
nomad code-modeandnomad code-mode-exec. - Support both local workflows and hosting models on remote GPU servers.
Install
Nomad requires Python 3.12 or newer.
For CLI use:
uv tool install --python 3.13 nomad-scifm
nomad --help
For development from a checkout:
uv sync --all-groups
uv run nomad --help
Quick start
Launch the example server directly in MCP Inspector using stdio:
npx @modelcontextprotocol/inspector -- \
uv run --directory container/demo \
nomad serve nomad.yml
For the HTTP workflow and matching URSA configs, see Starting a Nomad server and Connect to a hosted Nomad server.
Start here by task
| If you want to... | Start here |
|---|---|
| Connect to a running Nomad server | Getting started |
| Host a new SciFM | Model builder guide |
| Use Nomad for Inference | Nomad inference notebook |
| Browse CLI, config, and API docs | Reference |
| Run the demo deployment | Deployments |
| Work on Nomad itself | Developer docs |
Development
Useful commands from a repo checkout:
uv run --only-group lint just lint
uv run --group dev just test
uv run --no-dev --group docs just docs
uv run --no-dev --group docs just docs-pdf
Notice of Copyright Assertion (O5119)
© 2026. Triad National Security, LLC. All rights reserved.
This program was produced under U.S. Government contract 89233218CNA000001 for Los Alamos National Laboratory (LANL), which is operated by Triad National Security, LLC for the U.S. Department of Energy/National Nuclear Security Administration. All rights in the program are reserved by Triad National Security, LLC, and the U.S. Department of Energy/National Nuclear Security Administration. The Government is granted for itself and others acting on its behalf a nonexclusive, paid-up, irrevocable worldwide license in this material to reproduce, prepare. derivative works, distribute copies to the public, perform publicly and display publicly, and to permit others to do so.
Metadata
Release files for nomad-scifm 0.2.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| nomad_scifm-0.2.1.tar.gz | 119.9 kB | With provenance | Details for nomad_scifm-0.2.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| nomad_scifm-0.2.1-py3-none-any.whl | Python 3 | none | any | Details for nomad_scifm-0.2.1-py3-none-any.whl |
Total release size: 220.8 kB
Release files / nomad_scifm-0.2.1.tar.gz
| Download URL | nomad_scifm-0.2.1.tar.gz |
|---|---|
| Size | 119.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
5702318258cc9a17c5abb4392bc5810a606df66adc4ef72b1ed8d6cb0373a8fd
|
|
BLAKE2b-256 checksum How to use checksums |
ef4e9f865b1a6fbf6058f2a880c6c4327eb3f065e72d1ca8e9d74de03f0ea9a7
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 29, 2026.
Transparency logRelease files / nomad_scifm-0.2.1-py3-none-any.whl
| Download URL | nomad_scifm-0.2.1-py3-none-any.whl |
|---|---|
| Size | 100.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
055be80c786ff30d450584cdf94eb278ed117d2563a971db341ec866aff6bf44
|
|
BLAKE2b-256 checksum How to use checksums |
324e05dc7682f5370c0d98ac7cbb205c63e97af73f569b3396ea964ed235d40b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 29, 2026.
Transparency logSecurity for nomad-scifm 0.2.1
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.
Full provenance
All 2 files in this release have been uploaded with provenance metadata.
Attestation for nomad_scifm-0.2.1.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 29, 2026.
Transparency logA 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.