Show HN: Atomic – Self-hosted, semantically-connected personal knowledge base (github.com)

by kenforthewin 27 comments 152 points
Read article View on HN

27 comments

[−] redm 56d ago
This is pretty cool!

What's holding me back from AI repos and agents isn't running it locally though. Its the lack of granular control. I'm not even sure what I want. I certainly don't want to approve every request, but the idea of large amounts of personal data being accessible, unchecked, to an AI is concerning.

I think perhaps an agent that focuses just on security, that learns about your personal preferences, is what might be needed.

[−] kenforthewin 55d ago
Thanks for taking a look!

Agreed regarding the privacy/security hesitations. Running the models locally with ollama is an option, but of course there's the hardware requirements and limitations of open source models to contend with. ultimately it's a balance between privacy and ease of use, and I'm not sure that there's a good one-size-fits-all for that balance.

[−] cowpig 54d ago
Is this something like what you want?

greywall.io

[−] nikisweeting 51d ago
Yeah exactly like this. I like being able to approve/deny requests or "learn" from a good run and apply that policy to later runs so I can leave them unattended and know they can't access anything aside from what I approved.
[−] tedmiston 55d ago
is your idea of granular control (roughly) a group of agents in separate containers writing back to their own designated store each sufficient, or more control than that?
[−] rsafaya 53d ago
Great work. As someone who spends many hours a day in Claude Code and dreads the dreaded auto compact moment, the memory problem is genuinely a big point of frustration.

Right now I use a skill on every commit (or when the auto compact warning starts showing up) that forces Claude to update its "memory" . It is a flat markdown file that gets stuffed into conversations, not v smart. Claude forgets things I've told it dozens of times.

Your MCP server approach makes total sense. The create_atom tool alongside semantic_search makes it read/write from day one. I would love to wire a stop hook to automatically atomize session insights (the write side). That's the dream: I work on something in my code, Claude learns why, and that knowledge flows into Atomic without me saying "remember this."

[−] kenforthewin 53d ago
Thanks! Integrating Atomic with tools like claude code is one of the more exciting use cases in my opinion. There are a lot of tools for AI memory out there, but not a ton that allow you to browse, organize, and collaborate directly with the memories.
[−] aavci 55d ago
Does anybody mind explaining how the web of articles in the first image helps the writer?
[−] Notjoanbaez 55d ago
Nice ! Congratulations.

Not 100% sure what are the ingestions methods available ? Browser extension clipper and RSS are two. I guess I can manually create a node/atom ? Can it scan a local folder for markdown notes ? Or ocr some pdf -> markdown/frontmatter sidecar files -> atomic node ? That would be the dream.

[−] ata-sesli 54d ago
I like the headless approach here. Since you already have hierarchical auto-tagging, do those categories act as "gravitational anchors" for the spatial canvas to prevent a "semantic hairball" once the knowledge base scales beyond a few hundred atoms?
[−] jsmo 55d ago
This looks pretty neat! Thanks for sharing ^_^

I saw sqlite-vec for semantic search so I assume notes are stored in sqlite.

- What considerations did you have for the storage layer?

- Also does storage on disk increase linearly as notes/atoms grow?

[−] visarga 55d ago
I did something similar, markdown and code agents for memory, multiple feeds for intake, also my own browsing and claude cli messages get indexed.
[−] andreygrehov 55d ago
Great work, but your macOS build cannot be opened. You need to sign the app through Apple Developer Program.
[−] bdnk1 52d ago
Why not implement this on top of obsidian?
[−] ukuina 56d ago
Seems like a LogSeq/Roam/Obsidian alternative?