Hister – A private, full content search index that you control

Ohi, author here! Thanks for posting Hister. Feel free to A.M.A.

My first free software search project was Searx, a privacy respecting metasearch engine, but because of the limitations of the metasearch concept, I've decided to take a different approach.

Hister builds a personal search index from pages you visit, bookmarks, browser history, local files, and crawled websites. It stores extracted content with offline result previews, so information remains searchable even when the original page changes or disappears. It supports full text and semantic search, can run entirely on your own machine, and includes a web interface, command line tools, and an MCP endpoint for assistant integrations.

Project page: https://github.com/asciimoo/hister

Tiny read-only demo: https://demo.hister.org/

I just finished setting this up yesterday and I'm kind of obsessed with it. I was previously a heavy user of Karakeep, but I hated forgetting to save something and losing it. I also think Hister's semantic search is a better solution than AI generated summaries and tags. Support for local docs is super cool too, I have it set up to index my org notes directory.

Would be really cool to have Zotero library integration / import support!

I set this up a few months ago based on asciimoo's comments on HN, and barely used it at first, but I realized not too long ago that it could be a pretty useful research tool for one of my hobbies (award travel), that revolves around being in the know around various concepts and quirks.

I scraped and imported posts from the blogs I regularly reference for award travel, then hooked it up to OpenCode/Codex as an MCP server and used that corpus for research on those topics. So I can ask things like "has anyone ever mentioned running into this problem before?" [1]

If you have a hobby or working situation that requires you to regularly reference a core set of websites or reference materials, Hister provides almost all the tools out of the box to start a search engine against it. The default datasets they promote include the Python Stlib, MDN and RFC corpus, as an example. [2]

[1]: https://wmchen.com/blog/revisiting-hister/

[2]: https://hister.org/datasets

Is the design vibe coded in Codex by any chance? Seeing a lot of similar designs out there and it’s really starting to annoy me.

I have created something similar, yet different. I maintain my own Internet domain index.

https://github.com/rumca-js/Internet-Places-Database

Also I maintain android app that can be used to search places.

https://f-droid.org/en/packages/io.github.rumcajs.offlineweb...

I believe hister you have to fill in with your data, right?

I tried this out this week and liked it but really wish this project had some form of auth. Opening the contents of every page you’ve ever visited, even to the local network, is not the best idea.

Ooh I’ve been thinking about this idea for years, I’m glad someone beat me to it. Guess I have something to play with over the rest of the weekend!

I LOVE the concept. I will play around with the execution, if it works as described this is a great product.

Time to shameless plug my own easy to host your own content search index

Webtm.io

All open source and small enough to deploy. I deploy to cf webworkers so it’s the only place it’s tested.

One cool thing is we work on iOS, chrome and friends, Firefox and pretty much everywhere. We do require you bring your own LLM though.

Can it import browser bookmarks? It says browser history and a bunch of other bookmark services but not specifically browser bookmarks.

I am guessing the author didn't do a lot of research on the name as "Hister" is a name that people link to Hitler through Nostradamus: https://www.history.co.uk/articles/did-nostradamus-really-pr...

Got enough Hitler in my life with Google...

This is like Hipster. But missing a 'p'.