Skip to content

Local AI integration via Ollama for task and project assistance #2467

@alainm23

Description

@alainm23

Prerequisites

  • I have searched the existing issues and this feature has not been requested yet

Is your feature request related to a problem?

Managing tasks and projects often requires manual effort for things that could be automated — writing subtask breakdowns, summarizing project progress, or improving task descriptions. There's no way to get intelligent suggestions inside Planify without leaving the app.

Describe the solution you'd like

Integrate local AI assistance via Ollama — a tool that runs open source language models entirely on the user's machine, with no internet connection or API key required.

Possible use cases:

  • Suggest subtasks automatically from a task title
  • Generate a project description from its name
  • Summarize project progress based on completed and pending tasks
  • Improve task titles or generate descriptions from a short note
  • Natural language parsing in Quick Add for more complex inputs

The integration would be completely optional — if Ollama is not installed or not running, no AI features are shown and the app behaves exactly as today.

A settings section would allow users to configure the Ollama model to use (default: llama3.2:3b) and see the connection status.

Alternatives you've considered

External AI APIs (OpenAI, Anthropic, Gemini) could also be supported as an opt-in option for users who prefer cloud-based models, with a clear privacy warning that data leaves the device. However, local inference via Ollama should always be the default and recommended option given the privacy expectations of the Linux community.

Additional context

Privacy is a first-class concern here. All processing with Ollama happens locally — no data ever leaves the user's machine. This aligns with the values of the Linux/FOSS community and differentiates Planify from cloud-dependent task managers.

We'd love to hear from the community: what AI-assisted features would be most useful to you? Are there other local inference tools you'd prefer over Ollama?

Metadata

Metadata

Assignees

No one assigned

    Labels

    Projects

    Status

    Backlog

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions