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.
I am a 'fan' of Open Web UI, but the document editing mode is a compelling feature that Open Web UI does not have. I'll probably wait a while before trying Odysseus... let the inevitable security problems work themselves out.
Is the person best known for exploiting security vulnerabilities to get into places you'd rather they didn't, and then getting lost and taking forever to get places the ideal namesake for your AI workspace project?
I'm rereading the Iliad right now and was just reflecting on the fact the first time you see Odysseus at work he's selling two incompatible flavors of bullshit to officers and their men, in service of a third flavor of bullshit that was decided upon in advance at a war council.
The thing that intrigues me on this one is the Opencode roots.
I've currently host both Open WebUI and Opencode on a server setup and there's multiple things that Open WebUI has implemented very nicely over time but it was also prior to the emergence of coding agents / harnesses. As such, its strengths is more on the `/chat/completions` era and RAG and its own functions and ecosystem setup before tool calls were a thing.
If this stuff works for you already, I think that's fine. That's not a bad thing, and if anything, they've made attempts to improve esp. with the recent backend upgrades and projects like `open-terminal`.
However, Opencode has been built for the coding agent setup since its early days and Odysseus gives me more confidence to run sessions much better knowing that it runs on an Opencode core.
Stuff like MCP support and a clearer lifecycle for example are things I've never really seen implemented well on open-webui (they've improved and support this now, but I'm biased and am salty of the era from its early days of MCP support when they insisted you place a bridge (mcpo) in between just to make it do MCP.). In contrast, opencode does this very well since what they built that works on the terminal also applies to the desktop app and the ACP support for IDEs that use it to connect to the opencode harness.
At the minimum, I expect Opencode to work wonderfully against the frontier models, and all models they host on their Zen and Go service, so that adds some confidence as well on complex workflows.
In contrast, I still find model management a pain in the ass on open-webui (has always relied on LiteLLM or a third-party inference gateway) just to wrangle the models. Hell, they still tag the Responses API "experimental" today, a format that's been around since over last year.
Does that transfer to Odysseus? Maybe, maybe not. Seems it's based on it but a quick check on code says they merely adapted it so maybe it's the latter. I haven't tried it at depth and idk how well Pewds has implemented it, but if it improves on that angle and gets maintainers that accepts contributions from the community, I feel like it'll do nicely.
TL/DR - "cleaner and more polished" implies no vibe coded slop, and the only reason people start these projects in 2026 is because they're addicted to vibe slop coding.
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"
At least it's done by people who know what they are doing. AI content becomes slop when it's made by people who literally have no idea what is inside. To be honest, that's why most of the content is slop, hence branded AI slop.
> Fun fact: a chunk of Odysseus was built *from a phone* -- mobile shells (Termux), the PWA install, and on-device agents. So "works on mobile" isn't an afterthought, it's where a lot of it actually happened.
62 comments
[ 3.3 ms ] story [ 88.3 ms ] threadThere's already plenty of pimono / open code webui / electron wrappers
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.
I didn't see it linked from the project; it seems pretty relevant given who he is.
[1] https://www.youtube.com/watch?v=rAzT5lcezPs
Is the person best known for exploiting security vulnerabilities to get into places you'd rather they didn't, and then getting lost and taking forever to get places the ideal namesake for your AI workspace project?
I've currently host both Open WebUI and Opencode on a server setup and there's multiple things that Open WebUI has implemented very nicely over time but it was also prior to the emergence of coding agents / harnesses. As such, its strengths is more on the `/chat/completions` era and RAG and its own functions and ecosystem setup before tool calls were a thing.
If this stuff works for you already, I think that's fine. That's not a bad thing, and if anything, they've made attempts to improve esp. with the recent backend upgrades and projects like `open-terminal`.
However, Opencode has been built for the coding agent setup since its early days and Odysseus gives me more confidence to run sessions much better knowing that it runs on an Opencode core.
Stuff like MCP support and a clearer lifecycle for example are things I've never really seen implemented well on open-webui (they've improved and support this now, but I'm biased and am salty of the era from its early days of MCP support when they insisted you place a bridge (mcpo) in between just to make it do MCP.). In contrast, opencode does this very well since what they built that works on the terminal also applies to the desktop app and the ACP support for IDEs that use it to connect to the opencode harness.
At the minimum, I expect Opencode to work wonderfully against the frontier models, and all models they host on their Zen and Go service, so that adds some confidence as well on complex workflows.
In contrast, I still find model management a pain in the ass on open-webui (has always relied on LiteLLM or a third-party inference gateway) just to wrangle the models. Hell, they still tag the Responses API "experimental" today, a format that's been around since over last year.
Does that transfer to Odysseus? Maybe, maybe not. Seems it's based on it but a quick check on code says they merely adapted it so maybe it's the latter. I haven't tried it at depth and idk how well Pewds has implemented it, but if it improves on that angle and gets maintainers that accepts contributions from the community, I feel like it'll do nicely.
TL/DR - "cleaner and more polished" implies no vibe coded slop, and the only reason people start these projects in 2026 is because they're addicted to vibe slop coding.
https://lemonade-server.ai/
What the hell were you expecting. Your slop will fade in history... his slop will linger for months, maybe a year or two.
Then no one will care or remember about any of this.
https://github.com/pewdiepie-archdaemon/odysseus/commit/0517...
but with extra steps
This project is fun though! And the newest YT comments are very entertaining.