Skip to content

Feature Request: Auto-Populate Local Models via Ollama API #1883

@arky

Description

@arky

Currently, users must manually type the model names (e.g., gemma3, llama3.2) when adding a local agent provider. This is error-prone and requires users to check their Ollama inventory separately before configuring Dagu.

I would like Dagu to automatically fetch and display available models when the local provider is selected and a valid Base URL (like http://localhost:11434) is provided.

https://docs.ollama.com/api/ps

If the API returns exactly one model, Dagu should automatically select it as the default to streamline the setup process.

This feature would complement the "Local" provider type perfectly, making the Dagu Agent setup nearly zero-config for Ollama users.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions