Show HN: Deta Surf – An open source and local-first AI notebook (github.com)
We got frustrated with the fragmented experience of exploring & creating across our file manager, the web and document apps. Lots of manual searching, opening windows & tabs, scrolling, and ultimately copying & pasting into a document editor.
Surf is a desktop app meant for simultaneous research and thinking to minimize the grunt work. It’s made of two parts:
1) A multi-media library where you can save and organize files and webpages into collections called Notebooks.
2) A LLM-powered smart document which you can auto-generate using the context from any stored page, tab or entire notebook. This document contains deep links back to the source material — like a page of a PDF or timestamp in a YouTube video. Unlike Deep Research products (or NotebookLMs chat) the entire thing is editable. The user also stays in the loop.
With a technology like AI, context / data is proving to be king. We think it should stay under the user’s control, with minimal lock in: where you can own & export, and plug & play with different models. That’s why Surf is:
- Open Source on GitHub - Open (& Local Data): the data saved in Surf is stored on your local machine in open and accessible formats and mostly works offline. - Open Model Choice: you can choose which models you use with Surf, and can add custom & Local LLMs
Early users include students & researchers who are learning and doing thematic research using Surf.
Github repo: https://github.com/deta/surf/
Website: https://deta.surf/
22 comments
[ 4.0 ms ] story [ 48.4 ms ] threadThe benefits of this is that I can connect this data, but in a computable medium. Does your product have any similar ability to bring code workflows "inside" the Surf application?
Atuin: https://github.com/atuinsh/desktop
I would call this a note-taking app rather than a notebook, which to many mean computational notebooks like Jupyter.
I still don't see the advantage I get for my local system? Nearly all of the actions on the demo page are doable with chatGpt in one or three interactions.
Regarding open models: what is the go-to way for me to make Surf run with qwen3-vl? Ollama?
As far as I understand any endpoint that supports the completions API will work?
https://github.com/deta/surf/blob/main/docs/AI_MODELS.md
If I attach image context will it be provided to qwen3-vl? Or does this only work with the "main" models like OpenAI, Anthropic, Gemini and so on?
They didn't pivot, they completely reinvented themselves. Twice.
I loved their first cloud offering, which they sadly abandoned.
Then they launched Space, which was kinda cool, but mostly weird and raised the question "why?". Also cancelled.
Surf looks mostly cool, although I also don't quite understand it. It seems like Notion with a different twist on AI. Not sure. Since I'm fairly happy with my Obsidian + Codex setup, I'll pass for now. The good news is, this one's open source!
I'd love to know how they're financing all of this. They have been around for years and users never even had the option to drop money in their lap. Now they're trying open source. Wild ride.
All the best!
PS: I would have paid for deta cloud Pro ;)
In my experience, sorta kinda for certain uses but not entirely replacing other options. Marimo is great for when you want to build a more "app-like" notebook that does a task repeatably (it really beats Jupyter at this, even given JupyerWidgets), but for pure experimentation and playing with code, Jupyter Labs still rules the roost for me. I keep both installed for the different purposes that each excels at. This one may fill yet another need. Dunno yet until I give it some play-time.