Live data from Hacker News

Odysseus – self-hosted AI workspace

github.com

71–80 of 120 posts

Re: Odysseus – self-hosted AI workspace

#72

Why not just use open webui?

Surprisingly, there's a lot of items I'm seeing at first glance here at Odysseus that open-webui either doesn't have or takes extra effort to add in and I've used the latter for a really long time already.

Stuff like an agent mode, deep research and document work are things you'd be able to have with open-webui as well but Odysseus seems to have them thought out.

Re: Odysseus – self-hosted AI workspace

#73
post #16

Why not just use open webui?

Open webui isn't fully open source, because it doesn't allow you to change or remove Open Webui branding. I don't know if that was a motivation for creating this, but it is a reason some people might choose not to use it.

Plus, if you look at OpenWebUI horror of a commit history, they don't often take external contributions.

Re: Odysseus – self-hosted AI workspace

#75

reminds me of the milla jovovich vibecoded ai memory project that got a little bit of hype but was mostly junk... guessing we're going to see a lot more "developer talked to a celebrity and came up with an idea for their money"

except pewdiepies actually the developer in this equation too, its not just attaching his name to it, hes building the projects

Re: Odysseus – self-hosted AI workspace

#76
post #50

Earlier quoted context omitted.

We are working on Msty Claw that's local, private, and no telemetry as well: https://msty.ai/claw

When was the first release of this? Parent mentioned "polished" so I'd assume something at least a 6-12 months old, but that looks kind of brand new.

This wasn't possible 12 months ago, and barely 6 months ago.

Re: Odysseus – self-hosted AI workspace

#77
Not hating because his project is very cool but this is just a python UI on top of other oss - I'm only saying this bc team at Princeton and I have been building wthis but ground up in rust with more utility and running more custom tools, app integration, custom kernels outperforming llamacpp much more here www.conifer.build
Post reply on HN