I have used kagi for quite a while now, and i use it pretty much exclusively. I was unhappy with google ignoring many terms in my search queries and giving me results that I generally considered to be 'intro' pages and generic content, even when my searches were very specific. I have found kagi much better. I dont use any of the advanced stuff like summarisation or ai stuff, i just want search results that have my keywords in them.
Google Search has been in decline since they came up with Google+ and removed the Plus Operator from Google Search at the same time (and replaced it with quotes that don't do the same thing). About 13-14 years ago.
My brief review of Kagi: I’m never going back to ad-supported search.
I rely heavily on internet search for my job, and Kagi has made everything so much faster that I’ve almost stopped thinking about the search engine entirely. Google search had become frustratingly ineffective, often requiring me to dig deep to find what I needed. With Kagi, it just works. I rarely have to scroll beyond the first few results. In fact, Kagi’s effectiveness has made me search even more—now, I use it naturally without considering other services.
While this article highlights some valid concerns people may have with Kagi, I think the service is solid enough that everyone should give it a try.
Kagi is a tough pill to swallow. Their search is hands down the best around, there's no other way around it.
That being said, $10/mo is also expensive.
The workaround I found is using Kagi Ultimate. I get access to Claude (and I'm still able to attach files + access a dozen other LLMs) for $25/mo, so I was able to cancel Claude and keep Kagi and get the best of both worlds from either product.
Side note: incredible that a small team like Kagi's can somehow use LLMs more effectively in search than a company that has years of search experience (i.e. Google)
I love it too, and I do think it's expensive, too.
A lot of people laugh at thinking $10 (USD) pm is expensive, of course it's not huge money for most people. The problem is Kagi is a kind of "vote" towards moving the internet away from the ad-supported crapware trying to spy on your every click and capture your attention non-stop. If you're trying to replace a lot of free services with paid services to cast said vote towards shaping the web into what it should be, these costs really add up.
After paying for search, email, supporting a creator or two (e.g. a podcast), and some software here or there, you can easily end up in the hundreds of dollars, then you look back and notice that at best you've saved yourself from a few annoying ads and maybe gotten a fractionally better service and at worst your experience is unchanged and you're just deriving some intangible satisfaction from having not been spied on (which at the individual level doesn't make much difference unless millions of people follow your lead) or supporting a creator you admire.
For my company, it's easy: I pay for the tooling my devs need. Overly simplified, I only pay 50-65 % of that, because expenses lower taxes. And compared to salaries, a few hundred $ is not a big deal. If I think about the time it saves us and how much money we can make in that time, it's a no brainer. Even just having people enjoy their work more pays off.
There's opportunity cost. Ad supported services are not overly incentivised to provide a quality product in the long run, so it's a safe assumption to make that they will waste your time to some degree, at least as they mature and enshittify. Some are great, eventually they all become bad, in my experience. It can be smart to use free stuff while it's still good, with an eye on migrating.
I don't know how much sense it makes to apply this opportunity cost thinking to your personal time. I don't really do that, but I do try to reduce time spent on anything that annoys me, and to do more stuff that brings me joy or pride, even if it's not economical. Life is short.
It is more expensive than $0, but if you value your time more than a dollar an hour, the time saved is worth more than $10. I've found I scroll a lot less and have fewer false positive sites where I click in and look around only to find it isn't what my search was looking for.
That is just for the basic search feature. TBH, I haven't even investigated its other features, like lens and the ai stuff.
Can't say I understand how $10/month is expensive.
Quality search results ultimately save time digging through poor quality search results. Add up 300+ searches per month and surely you're hitting minimum wage value at least.
Here, this. Small, focused teams usually deliver more output per person (or even overall) than larger ones. Less management overhead, clear goals and responsibilities, tendency to employ people with cross-disciplinary experience, hiring for talent and not checklists, etc.
> [...] can somehow use LLMs more effectively [...]
LLMs are an incredibly effective tool for the few areas where they do fit the problem. But there's so much "AI" hype going on, everyone is trying to cram it into anything and everything, running around with a hammer trying to smash things just in case they turn out to be a nail. Even the old-time players (who should know better) can't resist the urge.
It's almost like oligopolies faced with changing markets tend to start collapsing under their own weight.
There was a time when it was incredible that a small team like Google could somehow implement search more effectively than a company that has years of search experience (i.e. AltaVista)
In that case -- and probably in the case of Kagi vs. Google as well -- it was entirely dependent on focus. In the hypothetical situation where your goal changes from "provide the best possible search" to "beat Yahoo," your available resources will be used on different things, and then...
> Side note: incredible that a small team like Kagi's can somehow use LLMs more effectively in search than a company that has years of search experience (i.e. Google)
But Google is not a search company. It used to be, but now it's an ad company. I'm sure their LLM use serves their purposes right.
I'm discovering that Claude is included in Kagi Ultimate and this is also slightly blowing my mind... Probably going to do the switch.
The fact that it's expensive is true but for me largely compensated by the niceties of the service. I don't really like the fact that they use Yandex either but the other search engines are not really satisfying for me anymore.
I've used Kagi Pro for several months now and it's working great for my personal and professional needs. The only thing I'm missing is the shopping features but I can with that and switch back to Google when I'm looking to spend my money on physical goods...
For most people, no. Can you think of $10/m you spend on something less important than search? A couple coffees, a sandwich, HBO, Netflix, a drink, using two gallons of gas recreationally, etc
I almost never buy coffee. Rarely buy sandwiches out. I get HBO for $3/month now for 6 months and will cancel after. Netflix is $7/month, though the whole household uses that. Two gallons a gas can buy a lot of transportation to necessities for the kiddo. Though we have an EV and $10 gets us maybe 250 miles more or less of driving -- that's a lot.
No, $10 a month is not expensive. However, the problem is the amount of products and services that in the past you could buy once or buy and if you wish to upgrade to the next version you had to pay again have become less and less and subscription services have skyrocketed.
Most people I know can afford some of the luxuries you list, but only barely. If you have to choose between having a drink once a month at a place other than your own home, and having an ad-free search engine that actually works, you'll find that many people are thick enough to go for that drink.
For context, this is speaking from the Netherlands, where housing is relatively expensive.
Back in the beta they planned on launching with a $20-$30/month unlimited plan and they didn't think they'd be able to bring the price down. That was a little too expensive for me so I moved on. I like what they're doing and I'd pay $10/month but I just don't have a use for it anymore.
The agents (optional with a toggle) hooked up to the LLMs are fairly decent. They'll search, grab YouTube transcripts, read online dev documentation, etc.
I used Kagi for a year. It was a great experience, no ads, decent search results. I quit recently, when I discovered that they integrate with Yandex. I think it is unacceptable in the todays reality.
And I do not want my search experience and product I pay for be dictated by US foreign policy and relations in a given time. Why should a search engine company get involved in international relationship affairs?
I’ve been using Kagi for over a year now. I just don’t think about it most of the times, I search, I get what I’m looking for quickly, and I move on. That’s all I want and it’s delivered well, without ads.
I think their focus should be to reduce resource usage on their side and make servers cheaper to run. Not other shenanigans like t-shirt or FastGPT or whatever. They can then offer a more attractive price for general public, who has never paid for search before and gets caught in the headlights when they hear you pay. Because right now, they don’t even have 40k users and if it goes on with this tempo, while also burning their resources for AI-things, I am afraid they will not stay much longer. Don‘t get me wrong, I am okay with the 10$ I pay, but, come on… who needs a t-shirt of a search engine and two different AI-thingy?!
It's already dirt cheap at $10 per month. Businesses who want to be successful do not bargain on their prices to try to satisfy cheapskates who are never satisfied with anything else than free anyway. They set a fair price for their product and continue to improve the value they bring to real, paying customers.
With that said, they should of course reduce their operating costs when they can, just like any business.
10$ a month is not cheap for a search engine where theoretically bigger and older engines out there are available for „free“. 10 is also psychologically difficult to accept than, I don‘t know like 4.99 for example.
That‘s why it should be their focus to find a sweet spot, where it‘s still acceptable for general public to pull the trigger and subscribe and for them to keep doing this.
This is not a streaming service or whatever. Their starting point was to fight Google who don‘t give a fuck about privacy and show that it‘s possible to fix the search, which Google fucked up during the years. I am also a subscriber because of this mindset, not just because it is a „product“ of a business who wants to be successful. At least that‘s what Kagi & CEO looks like at the moment.
My criticism is directed to AI and the stuff they are working on. Because of all these AI and shenanigans, they are focusing their valuable time to something other than becoming the big guy in privacy sphere. Customer counts show that. And I am 100% sure that if Kagi would cost 4,99$ a month, we would be talking about hundreds of thousands of users already.
Funnily enough I quite like my Kagi t-shirt. Especially because it does not look like a tech company shirt at all. Could they do better things with their time and money? Probably. Do I care? Not really.
But, I don't care about AI integrations either. I just like having decent search. And happy to pay for it as they seem to be doing things in the right spirit.
I am personally fine with the cost too, since I can afford it. My concern is that, they will go out of business because of these things. I would be really sad if that happens.
Yeah I thought the t-shirt move was ridiculous, but it's genuinely a very high-quality shirt. I'd like all my company shirts to be made by them. It's still a bizarre unrelated business decision, but at least they nailed it.
Agree about not being interested in AI integrations. I pay for a quality search engine, and I am happy with that product at the moment.
> I think their focus should be to reduce resource usage on their side and make servers cheaper to run.
I'd like for them to expose their result cache. Lately I've hit a run of pages that have updated my result away. I have a result-blurb with the search result; I could use what comes before and after it.
I'd pay $10 in a heartbeat if Kagi reliably used all my search keywords. But they don't, and I don't understand it. Just use all my words except stop words. I took the trouble to type them in.
I don't care if your coverage isn't as good as Google in its heyday. "0 search results" should be a mark of pride now.
It’s highly annoying to me as well. I’m still paying for now, but since they started (I was using them in Beta), they’ve been slowly using towards the mainstream "implicit" behavior and away from "explicit" behavior. I now see myself quoting terms far more often, which has other disadvantages (no typo correction, diacritics becoming relevant, etc.).
It’s the same for regional searches. Used to be (until Dec 2023) I could search for an ambiguous term (e.g. a product name that’s the same in English and German) with "!de" for German regional search and get German results. Now that’s impossible as most results will be the same English pages I’d get with my normal international or US region.
Overall just not a fan of the direction they are moving in (which seems to be DDG with personalization and no ads, but no more expert search)
I find it interesting that another comment states that they love Kagi exactly because Kagi uses all their search terms as opposed to Google. Not doubting your experience here, but I wonder how those experiences can differ so much.
"The 300 search plan unfortunately just isn’t a very pleasant experience. I’d find myself wincing any time I accidentally typed a query I already knew the result of like Serious Eats Channa Masala into Kagi’s search during my metered month" "...do yourself a favor and jump straight into the $10 USD per month plan"
This exactly. I love using Kagi and felt the relief sweep over me when I went to unlimited. Well worth it to me.
I use DuckDuckGo or pretty much anything else that feels suitable at the time, but I never think about searching this hard. It sounds like using Kagi inserts a conscious awareness of the product you're using. You're not just in the middle of an activity (whatever you're searching for), you're consciously Doing A Search.
Switching to unlimited searches sounds convenient if you can handle the price, but then a sort of Amazon Prime conundrum emerges: since you're paying for one option, why would you want to go anywhere else?
Maybe that's why I see so much enthusiasm for Kagi: when people use it, it's conscious.
Readit News
I rely heavily on internet search for my job, and Kagi has made everything so much faster that I’ve almost stopped thinking about the search engine entirely. Google search had become frustratingly ineffective, often requiring me to dig deep to find what I needed. With Kagi, it just works. I rarely have to scroll beyond the first few results. In fact, Kagi’s effectiveness has made me search even more—now, I use it naturally without considering other services.
While this article highlights some valid concerns people may have with Kagi, I think the service is solid enough that everyone should give it a try.
That being said, $10/mo is also expensive.
The workaround I found is using Kagi Ultimate. I get access to Claude (and I'm still able to attach files + access a dozen other LLMs) for $25/mo, so I was able to cancel Claude and keep Kagi and get the best of both worlds from either product.
Side note: incredible that a small team like Kagi's can somehow use LLMs more effectively in search than a company that has years of search experience (i.e. Google)
A lot of people laugh at thinking $10 (USD) pm is expensive, of course it's not huge money for most people. The problem is Kagi is a kind of "vote" towards moving the internet away from the ad-supported crapware trying to spy on your every click and capture your attention non-stop. If you're trying to replace a lot of free services with paid services to cast said vote towards shaping the web into what it should be, these costs really add up.
After paying for search, email, supporting a creator or two (e.g. a podcast), and some software here or there, you can easily end up in the hundreds of dollars, then you look back and notice that at best you've saved yourself from a few annoying ads and maybe gotten a fractionally better service and at worst your experience is unchanged and you're just deriving some intangible satisfaction from having not been spied on (which at the individual level doesn't make much difference unless millions of people follow your lead) or supporting a creator you admire.
It's tough.
For my company, it's easy: I pay for the tooling my devs need. Overly simplified, I only pay 50-65 % of that, because expenses lower taxes. And compared to salaries, a few hundred $ is not a big deal. If I think about the time it saves us and how much money we can make in that time, it's a no brainer. Even just having people enjoy their work more pays off.
There's opportunity cost. Ad supported services are not overly incentivised to provide a quality product in the long run, so it's a safe assumption to make that they will waste your time to some degree, at least as they mature and enshittify. Some are great, eventually they all become bad, in my experience. It can be smart to use free stuff while it's still good, with an eye on migrating.
I don't know how much sense it makes to apply this opportunity cost thinking to your personal time. I don't really do that, but I do try to reduce time spent on anything that annoys me, and to do more stuff that brings me joy or pride, even if it's not economical. Life is short.
It is more expensive than $0, but if you value your time more than a dollar an hour, the time saved is worth more than $10. I've found I scroll a lot less and have fewer false positive sites where I click in and look around only to find it isn't what my search was looking for.
That is just for the basic search feature. TBH, I haven't even investigated its other features, like lens and the ai stuff.
Quality search results ultimately save time digging through poor quality search results. Add up 300+ searches per month and surely you're hitting minimum wage value at least.
The value proposition is absolutely there at $10.
Not sure what I'll do when Grok 3 comes out (I expect it to beat every other LLM out there hands down) but we'll see by then :p
Here, this. Small, focused teams usually deliver more output per person (or even overall) than larger ones. Less management overhead, clear goals and responsibilities, tendency to employ people with cross-disciplinary experience, hiring for talent and not checklists, etc.
> [...] can somehow use LLMs more effectively [...]
LLMs are an incredibly effective tool for the few areas where they do fit the problem. But there's so much "AI" hype going on, everyone is trying to cram it into anything and everything, running around with a hammer trying to smash things just in case they turn out to be a nail. Even the old-time players (who should know better) can't resist the urge.
It's almost like oligopolies faced with changing markets tend to start collapsing under their own weight.
But the API is tempting for a cost savings.
I put $5 in API for “Continue” extension in VS Code and it’s been months and haven’t used it all up yet.
But Google is not a search company. It used to be, but now it's an ad company. I'm sure their LLM use serves their purposes right.
The fact that it's expensive is true but for me largely compensated by the niceties of the service. I don't really like the fact that they use Yandex either but the other search engines are not really satisfying for me anymore.
I've used Kagi Pro for several months now and it's working great for my personal and professional needs. The only thing I'm missing is the shopping features but I can with that and switch back to Google when I'm looking to spend my money on physical goods...
For most people, no. Can you think of $10/m you spend on something less important than search? A couple coffees, a sandwich, HBO, Netflix, a drink, using two gallons of gas recreationally, etc
For context, this is speaking from the Netherlands, where housing is relatively expensive.
Back in the beta they planned on launching with a $20-$30/month unlimited plan and they didn't think they'd be able to bring the price down. That was a little too expensive for me so I moved on. I like what they're doing and I'd pay $10/month but I just don't have a use for it anymore.
From experience on the figurative side of this reality, I can attest that it is hard to build a track while the train is running on it.
The agents (optional with a toggle) hooked up to the LLMs are fairly decent. They'll search, grab YouTube transcripts, read online dev documentation, etc.
https://news.ycombinator.com/item?id=42349797
https://kagifeedback.org/d/5445-reconsider-yandex-integratio...
I want small web search. I want good results. I will pay for search!
I do not want to support Russia.
Dead Comment
One interesting initiative I discovered is that Qwant and Ecosia are teaming up to develop a new independent European search index:
https://betterweb.qwant.com/en/2024/11/08/ecosia-and-qwant-j...
Very much look forward to see this :)
I think their focus should be to reduce resource usage on their side and make servers cheaper to run. Not other shenanigans like t-shirt or FastGPT or whatever. They can then offer a more attractive price for general public, who has never paid for search before and gets caught in the headlights when they hear you pay. Because right now, they don’t even have 40k users and if it goes on with this tempo, while also burning their resources for AI-things, I am afraid they will not stay much longer. Don‘t get me wrong, I am okay with the 10$ I pay, but, come on… who needs a t-shirt of a search engine and two different AI-thingy?!
With that said, they should of course reduce their operating costs when they can, just like any business.
That‘s why it should be their focus to find a sweet spot, where it‘s still acceptable for general public to pull the trigger and subscribe and for them to keep doing this.
This is not a streaming service or whatever. Their starting point was to fight Google who don‘t give a fuck about privacy and show that it‘s possible to fix the search, which Google fucked up during the years. I am also a subscriber because of this mindset, not just because it is a „product“ of a business who wants to be successful. At least that‘s what Kagi & CEO looks like at the moment.
My criticism is directed to AI and the stuff they are working on. Because of all these AI and shenanigans, they are focusing their valuable time to something other than becoming the big guy in privacy sphere. Customer counts show that. And I am 100% sure that if Kagi would cost 4,99$ a month, we would be talking about hundreds of thousands of users already.
But, I don't care about AI integrations either. I just like having decent search. And happy to pay for it as they seem to be doing things in the right spirit.
Agree about not being interested in AI integrations. I pay for a quality search engine, and I am happy with that product at the moment.
I'd like for them to expose their result cache. Lately I've hit a run of pages that have updated my result away. I have a result-blurb with the search result; I could use what comes before and after it.
I don't care if your coverage isn't as good as Google in its heyday. "0 search results" should be a mark of pride now.
It’s the same for regional searches. Used to be (until Dec 2023) I could search for an ambiguous term (e.g. a product name that’s the same in English and German) with "!de" for German regional search and get German results. Now that’s impossible as most results will be the same English pages I’d get with my normal international or US region.
Overall just not a fan of the direction they are moving in (which seems to be DDG with personalization and no ads, but no more expert search)
[1] https://kagifeedback.org/
[2] https://kagi.com/changelog
Say something negative about google, receive karma.
No place with this kind of system should be relied on for veracious claims.
I've added a few, but I worry that adding more is counterproductive. Maybe it would help them prioritize if more people chimed in.
This exactly. I love using Kagi and felt the relief sweep over me when I went to unlimited. Well worth it to me.
Switching to unlimited searches sounds convenient if you can handle the price, but then a sort of Amazon Prime conundrum emerges: since you're paying for one option, why would you want to go anywhere else?
Maybe that's why I see so much enthusiasm for Kagi: when people use it, it's conscious.
On unlimited for a few months now and it is so much nicer to not worry about it anymore.