← AI GitHub

AI GitHub

Open Notebook for source-based research

Collect research sources into notebooks and turn selected material into notes or audio.

By

Local AIPublished 2 min read

Key Takeaways

  • The self-hosted application keeps sources, notes and conversations organized by notebook.
  • Start with a source library small enough to audit manually.
  • Ask for a comparison with source references, then use a saved note to test how the same material is represented in another format.
  • The source library and the model endpoint can live in different places.

How it works

The self-hosted application keeps sources, notes and conversations organized by notebook. Model settings and transformations determine how material is processed and which provider handles generation.

What you need

Start with a source library small enough to audit manually. Text generation and audio production can use separate providers, so check both configurations if you plan to generate recordings.

What to try first

Add two short sources that disagree. Ask for a comparison with source references, then use a saved note to test how the same material is represented in another format.

Export or copy a note and verify its source references outside the application. This is useful if the notebook is an intermediate step in a research workflow.

Where to look for failures

The source library and the model endpoint can live in different places. Verify where uploaded text is stored and sent, and inspect generated audio against the underlying notes.

Related Franklin pages

Use the same two or three documents in each workspace. Comparing source passages, index updates and data flow reveals differences that a fluent chat answer can hide.

For more on how model size affects deployment decisions, read Franklin’s guide. Small language models

Project documentation

Try it for your workflow

Explore the project’s documentation for setup and usage, or save this page to a collection for later.

Read the project documentation ↗