I've never understood what niche Orion is supposed to fill. People who value privacy would be more likely to use an open-source browser. Firefox and Brave already serve that purpose. Maybe it's less important to Mac users, but on Linux, a proprietary browser is a major deal-breaker for most people. Plus, it's less convenient if the browser isn't simply included in the repository as a result. Orion should have been developed as open source from the start, with community involvement. Kagi can still benefit from this, though, by serving as the default search engine in exchange for funding the development, and by having the Kagi Assistant directly integrated into the platform.
Anecdotally, the niche it solved for me for a while was "Safari for optimal performance on mac, but with proper extensions like ublock".
I used it regularly for almost a year, eventually got off because of some UI bugs that came up and because the Safari dev tools feel so clunky/need relearning compared to Chrome & FF.
I’ve been using it on iOS since it’s near inception and I can report that it is much more stable now than it was since its original release. I tried to live on the desktop browser, however, and eventually had to declare it unusable and switch back to Firefox. Mostly around things like 1Password and similar extensions being pretty broken in the Orion desktop browser.
I've been paying for kagi since it came out, use linux on my laptop and lineaege on my phone, and I don't use Orion.
In other words, as you say, exactly.
I have no idea if it's a good or bad or I'd like it or not. I never even considered trying. I don't mind that it exists. I don't think kagi are doing anything bad with it. But I also just have no interest in even trying it. Presumably it's good for soneone but for me (a paying kagi customer linux user) it's almost like it's invisible. A probably benign, utterly uninteresting thing.
I don't use any of their AI features either. I hope they cost extra seperately so that I'm not paying for that stuff I'm not using but I suspect I probably am.
Kagi subscriber here. I think mature technologists should stop supporting proprietary browser technology workarounds, and I personally wont support them although I like the spirit of what Kagi tried to do with Orion on Mac OS.
We dont need ad blockers. We need advertiserproof/trackingproof browsers. Like we have waterproof shoes and coats and hats. We could also use some nicer browsers in terms of features.
But what folks who really care about these details should do is simply de-apple, and de-google (and obviously de-windows!). That will get you much further than using a particular browser, but a good browser helps.
I’ve been a long-time subscriber to kagi, but also a long-time critic that they bite off more than they can chew. Relatively happy to see this, and I’m sure there’ll be an open-source community willing to carry on the Linux work.
Lately I haven't been very happy with Kagi. A few searches have completely failed for me returning a blank page when both DuckDuckGo and Google had a response. The Kagi translate on/off switch made me think their services are unreliable. Then this happens and it feels like more that their word is unreliable. They expanded into too many domains and spread themselves too thin and that doesn't give me confidence.
My subscription is up for renewal in December and I think I actually have a decision to make. For now I'm very happy with the Kagi MCP for my research agent. But I'm definitely having a moment of "how reliant should I really be on this company?"
If you're mainly using the MCP, it could be worth making your own MCP that uses your own API keys from Brave, Mojeek & Marginalia (optionally also add Yep). For the most basic ranking, get it to group URLs that appear in more than one search engine and list those ones at the top. Your favorite AI will be able to vibe-build this all for you and give you an exe / binary you can run as an MCP that runs locally over stdio.
If you try it out, you'll either find a replacement that saves you money, or you'll at least have the makings of an escape plan if you need it later. You'll also have your own comparison data for where Kagi beats a generic metasearch, and if that difference is meaningful for you.
I wish they would cancel the Mac version as well. It really has no clear purpose and just further dilutes the "alternatives to Chrome" space. If they have money to spend on a browser, why not put that effort into a browser that actually has a chance to tilt the scales a bit, like Zen?
I want the same browser (port) on each of my OSes. No Linux/AOSP port means I won't use your browser. But I guess I wasn't interesting enough of a customer (am subscribed to Kagi Search). No problem. For example: on my Steam Deck, I am happy with Mozilla Firedox and uBlock Origin. This company pivots too much to USA to my taste anyway.
As ex-Kagi subscribers, I could no longer see the value in paying $10, as the results weren’t significantly different from those on my self-hosted SearXNG.
> We also chose to build it the hard way by not forking Chromium.
Bad call, because it's genuinely too hard for someone the size of Kagi, as they've discovered.
There's room for a Chromium fork that has a better reputation than Brave. (I use Brave, and it's great, but I realise many people don't want to use it.)
The struggle is the blind opening of chrome, like most people probably just do without thinking. Unless you are really a hardcore frontend developer, you lose nothing by switching to Firefox (or non chrome/chromium browser). I operate both and for 95%, maybe even more, there is no difference. By switching you will put pressure on google to keep on the users good side.
Like others in this thread I’ve questioned why Kagi is developing a browser. My only guess is they at one point thought there would be some opportunities in integrating AI stuff and a browser. Because their CEO has said in the past that they are convinced of LLM usefulness but in a specific way.
I wouldn’t be surprised to see some agentic features in their browser at some point. Their assistant tool is already quite good - it has replaced search for me in a number of scenarios.
The way I remember it marketed, and the way I originally found it, was as a workaround to setting the default search on iOS. This was before I was conscious of AI and before I remember it being in any of Kagi’s products.
I ended up staying because the Adblock is good (search remains good). The browser is fine. It does have bugs and needs to be hard closed occasionally.
I agree on the assistant. It is very capable. I use the Kagi mcp with coding agents and I like the results, but they have done something with their assistant that makes it even more useful.
I don't understand the reasoning behind Kagi developing a browser. Such a small team would gain more from partnering with the likes of Mozilla/Vivaldi/etc IMO
Google was vastly better resourced though when they started Chrome. They even waited for many years because Eric Schmidt thought the company was still too small to enter the browser wars.
Sad that the other two platforms won't have the same stewardship as Orion on macOS. Especially since we're likely to see drift from the core WebKit implementation between them now.
I don't understand the decision to open source the Linux and Windows ports, but not the MacOS version. They should have moved their Orion development into the open, and said we're not going to support Linux and Windows going forward. Then someone else could have picked up the task of keeping the Linux and Windows forks in sync with their MacOS work.
Maybe it is for better. I used Orion as my main browser for awhile on iOS, but then it started getting weird bugs. Now I have both Safari and Firefox open all the time and watch yt on Brave.
I try to see if they got Orion to behave again, but find a bit difficult to trust it as the main browser.
I found the move to release Orion on Linux and windows weird.
If you were Google and you wanted to spread your search engine to the world, it would be fine but such a small company. And the market share would still have been abysmal on the platforms.
Great thing that they release it before abandoning it, truely a great move !
And hopefully they keep making it better on macOS and iOS.
> If you were Google and you wanted to spread your search engine to the world, it would be fine but such a small company.
I've done successful, safe cross-platform development at several small companies and it goes just fine. But you do need capable hands at it and some developers really worked their best to sabotage the work platforms due to sheer laziness.
Size of company is irrelevant, not hiring fanboys is the most important part at this process. I wonder how Kagi managed to fail at that.
I used it regularly for almost a year, eventually got off because of some UI bugs that came up and because the Safari dev tools feel so clunky/need relearning compared to Chrome & FF.
In other words, as you say, exactly.
I have no idea if it's a good or bad or I'd like it or not. I never even considered trying. I don't mind that it exists. I don't think kagi are doing anything bad with it. But I also just have no interest in even trying it. Presumably it's good for soneone but for me (a paying kagi customer linux user) it's almost like it's invisible. A probably benign, utterly uninteresting thing.
I don't use any of their AI features either. I hope they cost extra seperately so that I'm not paying for that stuff I'm not using but I suspect I probably am.
Yes, it's good, and I'll keep using it for the foreseeable future, but it's not an unassailable lead.
We dont need ad blockers. We need advertiserproof/trackingproof browsers. Like we have waterproof shoes and coats and hats. We could also use some nicer browsers in terms of features.
But what folks who really care about these details should do is simply de-apple, and de-google (and obviously de-windows!). That will get you much further than using a particular browser, but a good browser helps.
My subscription is up for renewal in December and I think I actually have a decision to make. For now I'm very happy with the Kagi MCP for my research agent. But I'm definitely having a moment of "how reliant should I really be on this company?"
If you try it out, you'll either find a replacement that saves you money, or you'll at least have the makings of an escape plan if you need it later. You'll also have your own comparison data for where Kagi beats a generic metasearch, and if that difference is meaningful for you.
Bad call, because it's genuinely too hard for someone the size of Kagi, as they've discovered.
There's room for a Chromium fork that has a better reputation than Brave. (I use Brave, and it's great, but I realise many people don't want to use it.)
We need more rendering engines out there in the wild, as the situation with chrome's monopoly is already critically dire.
Mozilla have more momentum, experience, and funding, but still struggle.
[1] https://github.com/imputnet/helium
I wouldn’t be surprised to see some agentic features in their browser at some point. Their assistant tool is already quite good - it has replaced search for me in a number of scenarios.
I ended up staying because the Adblock is good (search remains good). The browser is fine. It does have bugs and needs to be hard closed occasionally.
I agree on the assistant. It is very capable. I use the Kagi mcp with coding agents and I like the results, but they have done something with their assistant that makes it even more useful.
I try to see if they got Orion to behave again, but find a bit difficult to trust it as the main browser.
If you were Google and you wanted to spread your search engine to the world, it would be fine but such a small company. And the market share would still have been abysmal on the platforms.
Great thing that they release it before abandoning it, truely a great move !
And hopefully they keep making it better on macOS and iOS.
I've done successful, safe cross-platform development at several small companies and it goes just fine. But you do need capable hands at it and some developers really worked their best to sabotage the work platforms due to sheer laziness.
Size of company is irrelevant, not hiring fanboys is the most important part at this process. I wonder how Kagi managed to fail at that.