I ended up building my own search instead - whoever controls your search results also controls how you find information and what you see, so I felt I needed to start building my own index. If you don't want to go down that rabbit hole and don't mind Kagi's politics, $10/month is a small price to pay to get a better search experience.
I started with a metasearch, since that's (mostly) all Kagi is. I send prepaid-API calls to Brave, Mojeek, Marginalia & Yep for every query, and get about 200 results back on every search. The cost is far less than I paid Kagi. My first version was a single PHP file written by Claude Sonnet 3.6 (!), any modern AI would one-shot something dramatically better. Obviously you can iterate & improve it over time yourself. Grouping the results by domain and ranking by how many search engines return the same page/domain will get you ~60% of the ranking quality.
Over the years I added more ranking signals and had Claude build a ranking optimizer. I provide "golden queries" ranked as I would prefer, and the optimizer runs experiments to optimize the weights for each ranking signal. It isn't perfect, especially since I only use on-page signals. But it has been good enough that I don't miss Google.
My own index is just a couple of SQLite databases. It is ridiculous how far you can get with SQLite, FTS Full Text Search & its built-in BM25. Each webpage takes up 10KB of index storage on average, once trimmed down to just the indexable text. I never clear my Firefox history, so I went through my history cache to find which sites I actually visit, then made a command line indexer to run on my laptop and index them in the mornings. Most sites offer a sitemap or RSS file, so you don't need to worry about crawling the site. My tiny index doesn't answer every query, and that's what the metasearch is for. But surprisingly often, that tiny subset of the internet does have the answer I need, and it saves me a paid search API fee every time it does.
My system is held together with duct-tape and hope, so for most people it's easier just to use Kagi (or Uruky.com). If you do want to build it out, the blog at marginalia.nu has far more useful technical details than anything I can offer. But if you do go down the rabbit hole, I think you'll start questioning how a giant enterprise like Google can manage to screw up search so much.
I treat my Firefox History the same way though the way I use it is a bit different right now. I would like to harness it like yours, but first I think I need to pipe it into ArchiveBox or something
Aside from the obvious larger issues with Gmail (privacy, trusting that Google won't just deactivate your account, etc), is there anything in the day-to-day usage of Fastmail that you find to be an improvement over Gmail, in the same way that Kagi is an improvement over Google search?
This massively improves your security.
You can keep the actual email that you use to log into fastmail completely secret and never use it anywhere which makes it harder for people to attack your fastmail account.
- Bring-your-own domain name with lots of useful features for aliases and routing messages around based on that
- Real human customer service, and with agents that actually want to help you to boot
- Everything follows common standards (IMAP, CalDAV, CardDAV), no need to deal with Google/Apple-specific weird stuff
- Masked email
- 60 GB storage per seat
- Actually usable and good web UI
kagi, for example, has "Quick Answer" mode, which means if you append "?" to whatever your asking about, it will generate a summary (sort of an on-demand AI injection), which is great for the user experience (nobody is shoving AI down your throat).
but the problem remains: am i really going to scour web results, or am i going to throw in a "?" and get my answer in less than 3 seconds? i find myself using this more and more, despite deliberately trying not to, the convenience of is just addictive like that.
the result for web site operators is the same: my click never arrived, the ads they served didn't reach anyone, and they are disincentivized to even run a site.
i'm not sure what's going to happen, but it's not looking great. the web was meant to democratize information. the current generation of LLMs/search/chats are reversing this, siloing the truth within the same 5 oligarchs of data.
> The thought of paying a subscription for search is abhorrent
I've found myself paying for more and more products that I used to get for free. Given how expensive running a search engine is ad revenue is necessary for a free product. Advertisers pay more if they are getting clicks and conversions... Obviously this ends up impacting search results. Additionally, the tradition SEO model went from bad to worse with LLMs.
Anyways, up until very recently I would've agreed with you, but ultimately this was a pretty easy expense to justify after a short trial.
I've been a happy customer of Kagi since 2022, and for me it's well worth the money. It gets better results than Google or DuckDuckGo, and I trust the results more because they're not pay-to-play like Google.