Show HN: Generate Fine-tunning dataset using deep research in terminal

Just open-sourced a small terminal tool I’ve been working on. The idea came from wondering how useful it’d be if you could just describe the kind of dataset you need, and it would go out, do the deep research, and return something structured and usable.

You give it a description, and it pulls relevant info from across the web, suggests a schema based on what it finds, and generates a clean dataset. The schema is editable, and it also adds a short explanation of what the dataset covers. In some cases, it even asks follow-up questions to make the structure more useful.

Started off as a quick experiment, but a few people found it interesting, so I figured I’d release this first version. It’s simple, fast, runs in the terminal, and is fully open source.

Repo is here: https://github.com/Datalore-ai/datalore-deep-research-cli, do give a star if u like it.

Also been playing around with the idea of local deep research, where it works offline or on top of your own files or saved pages. Might explore that more soon.

Would love to hear what you think or how you'd improve it if you give it a try.