Skip to main content

AI Models



An App for Nautobot.

Overview

AI Models makes Nautobot the source of truth for your LLM estate. It records which providers exist, how to reach each one, and which models each provider offers. Access control, change logging, custom fields, and the REST API all come from Nautobot.

The app is a data catalog. It has no AI or LLM client code and it does no inference. Another app, a Job, or an external system reads these records and does the work. This keeps the question what is available and allowed apart from the question how do I call it.

The app keeps no URL and no credential of its own. Each AI Provider points at a Nautobot External Integration. That integration gives the remote URL, the HTTP headers, the SSL verification, the CA file path, the timeout, and the Secrets Group. A provider also records its API dialect, so that a consuming app knows how to address the endpoint.

Each AI Model belongs to a provider. It carries a name, a description, and a kind of chat or embedding. It also carries an enabled flag, the cost of a million tokens, and the parameters to send with a call. num_predict and temperature fall back to the provider default.

The Discover AI Models Job reads GET /v1/models from each enabled, OpenAI-compatible provider and keeps the model list current. It creates and updates records. It never deletes one.

A second pair of models does the same for MCP. An MCP Server records one server and what it reported about itself. An MCP Tool records one tool that a server advertises, with both advertised JSON Schemas and the two flags that a person owns.

Screenshots

The AI Providers list. Each provider points at an External Integration. The Provider Type column says how a consuming app addresses the endpoint.

AI Providers list

The provider detail view lists each model that the provider offers.

AI Provider detail

The Discover AI Models job reads GET /v1/models and records what it finds. It never deletes a record.

Discovery job result

If the External Integration that you need does not exist, create it in a modal. You do not leave the provider form.

Create an External Integration from a modal

The MCP Servers list, and one server with what it advertised.

MCP Servers list

MCP Server detail

For more screenshots, read the Using the App page.

Documentation

The full documentation for this app is on Read the Docs:

Contributing to the Documentation

The Markdown source of the documentation is in the docs folder of this repository. For a simple edit, a Markdown editor is enough. Clone the repository and make the change.

To see the generated documentation site, build it with MkDocs. The invoke commands start a container that hosts the documentation on http://localhost:8001. The Development Environment Guide gives the details. The container rebuilds a page when you save a change, and your browser reloads it.

Pull requests with fixes or improvements are welcome.

Questions

For a question or a comment, read the FAQ first. You can also use the Network to Code Slack, in the #nautobot channel. If you have no account, sign up here.

Metadata

Release files for nautobot-ai-models 1.1.0

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

Source distribution (sdist)

Source distribution for nautobot-ai-models 1.1.0
File Size Uploaded Provenance
nautobot_ai_models-1.1.0.tar.gz 3.9 MB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for nautobot-ai-models 1.1.0
File Interpreter ABI Platform
nautobot_ai_models-1.1.0-py3-none-any.whl Python 3 none any Details

Total release size: 7.9 MB

Release files / nautobot_ai_models-1.1.0.tar.gz

Download URL nautobot_ai_models-1.1.0.tar.gz
Size 3.9 MB
Tags Source
SHA-256 checksum
How to use checksums
e8cbde18255037d4b0a480f158d6f0042da88434b6a706fdd30c368b5e526222
BLAKE2b-256 checksum
How to use checksums
4403ec478df289c00b6ca8cb8a56766df4f371f00197f175dc94c333f287d915
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via poetry/2.3.2 CPython/3.11.14 Darwin/25.5.0

Release files / nautobot_ai_models-1.1.0-py3-none-any.whl

Download URL nautobot_ai_models-1.1.0-py3-none-any.whl
Size 4.0 MB
Tags Python 3
SHA-256 checksum
How to use checksums
fdfb3f4d2c99a9501fdf69084124b7a0213fe57f65d686bf88aa595f8c792311
BLAKE2b-256 checksum
How to use checksums
571b874c864c0fe0a2d96c396586258836752aac0f6380c84a19938f6e7bea79
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via poetry/2.3.2 CPython/3.11.14 Darwin/25.5.0

Security for nautobot-ai-models 1.1.0

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.

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