How do you manage permissions in the wiki? Does it require all content being available to everyone in the org or does it do some sort of vectorizing that is unique to every single user based on their perms? Whenever we've tried to build something similar, permissions is usually the first headache and is often why something like Microsoft's WorkIQ is appealing (if you're an O365 org).
There is a lot of competition in this space, both commercial companies and open source. It seems like the biggest advantage for using one of these and not Claude or Codex is that you can use multiple models. Otherwise, those two have all the same features, or probably will in the next week.
Are you able to use multiple models? Or I guess the first question is, what model(s) are you using? At this point, many enterprises care so that should be front and center, especially if you're using models hosted in China, because a lot of non-Chinese companies care about that.
You mention some things about unique ways to store memory. Do you have any data or use cases on how that improves performance? If you do, you should get those on your website too.
I'm not sure you have a very strong answer to "Why not just run Claude or Codex on my laptop?" Sure, you provide compute, but so do they, and most enterprises and even regular people are getting desktops/droplets to run their agents now because of this problem. This is kind of solved already.
Also there is a small nit with your website. The graphic next to "Proactively gets things done for you" gets bigger and smaller, so if you're trying to read anything below that, it keeps jumping up and down.
If AI has achieved anything it's a dramatic increase in documentation quality for the sake of training or instructions.
I'd argue that if documentation on how to operate your business can be used to feed an agent, your problem was never the ability to run operations and the ROI will amount to the ability to ask instead of doing. I don't know how much this is gonna go for, but you could probably have one of your existing staff just do basic documentation lookups too.
The documentation is not just for lookup queries. Having this layer betters the quality of responses, but also enables a lot of features we have in Almanac/plant to add. I mentioned in the post how this layer enables proactive agents and long horizon tasks. I just came across a Google paper yesterday (https://arxiv.org/html/2608.27454v1) that use a similar wiki knowledge base to self improve agent skills. I think these are just scratching the surface of ideas of what's possible with this layer
Given that I don't know everything about my 4-person company, and that I never knew everything when it was a 1-person company (guess which person is that), this sound like https://x.com/mitchellh/status/2044529496217555333 (apologies for twitter link)
I would agree that there are a lot of people in this space, both products and roll your own. We are doing our own stuff here in our company right now, and could be interested. But for me, I didn't feel like i know enough to actually assess and take the next steps. Good luck!
It of course gets more magical the longer you use it, but we've felt it starts providing utility from first few days itself. It could identify things that are going on immediately in your life and help there
Just checked out WorkIQ, the promise is quite similar. Spend compute and time upfront developing the knowledge base, which will later result in much better answers
Given it has "logins" to tools without APIs (browser-based access), how do they handle 2FA, session persistence, and ToS violations for services that don't allow bot access?
Our browser is interactive, in the sense that one could click around the browser, as well as the agent. Usually for 2FA logins, Almanac would hand it over to the human, who'd complete login, and then continue.
We use Browserbase for the browser and session persistence is inbuilt.
For ToS violations, this is a limitation. Accessing sites that don't allow for bot access could result in account ban/suspension. Simply using Browserbase under the hood does not remove this risk.
Congratulations on the launch! The demo in the video you linked looks awesome (though your video resolution is a bit low, some of the text is hard to read on screen, I suggest you record in higher resolution). I think you made a really good choice to have your connector provider handle OAuth credentials, since it is really hard to get security right on a multitenant app like yours, where some of your agents are doing work on customers' behalf and others are improving your product itself :). The design of your app interface also looks really great!
Thanks! I saw the video again and can't look beyond the low resolution now lol. We knew from day 1 that trusting agents is going to be the most difficult part of our product, so we take privacy and security with the utmost seriousness
Are you able to use multiple models? Or I guess the first question is, what model(s) are you using? At this point, many enterprises care so that should be front and center, especially if you're using models hosted in China, because a lot of non-Chinese companies care about that.
You mention some things about unique ways to store memory. Do you have any data or use cases on how that improves performance? If you do, you should get those on your website too.
I'm not sure you have a very strong answer to "Why not just run Claude or Codex on my laptop?" Sure, you provide compute, but so do they, and most enterprises and even regular people are getting desktops/droplets to run their agents now because of this problem. This is kind of solved already.
Also there is a small nit with your website. The graphic next to "Proactively gets things done for you" gets bigger and smaller, so if you're trying to read anything below that, it keeps jumping up and down.
I'd argue that if documentation on how to operate your business can be used to feed an agent, your problem was never the ability to run operations and the ROI will amount to the ability to ask instead of doing. I don't know how much this is gonna go for, but you could probably have one of your existing staff just do basic documentation lookups too.
Given that I don't know everything about my 4-person company, and that I never knew everything when it was a 1-person company (guess which person is that), this sound like https://x.com/mitchellh/status/2044529496217555333 (apologies for twitter link)
OpenTag
Turnstone
Memory Store
Hyper
Hyperspell
Wato
Savant
Shepherd
Glen
OpenTag
Janet AI
screenpipe
Cerenovus
jo
Bond
Airweave
Mem0
Theta
Nessie
Mosaic
Onyx
Slite
Dashworks
Circleback
Stamp
Tasklet
Within
Khoj
We use Browserbase for the browser and session persistence is inbuilt.
For ToS violations, this is a limitation. Accessing sites that don't allow for bot access could result in account ban/suspension. Simply using Browserbase under the hood does not remove this risk.