PewDiePie’s AI ambitions have finally become a reality after months of documenting his journey into building his own free AI platform.
As revealed in a video titled “MY trillion $Dollar Project is finally OUT!”, PewDiePie has officially launched Odysseus, a free self-hosted AI workspace designed to give users an alternative to popular platforms like ChatGPT and Claude.
Over the last year, the YouTuber has been diving deep into AI development, building custom systems to run open source models on his own hardware, and aiming to create a tool that offered the same convenience as mainstream AI platforms without relying on cloud services or handing data over to major tech companies. Well, now that project has finally arrived. PewDiePie launches free self-hosted AI workspace Odysseus
According to the official description, “Odysseus is a self-hosted interface for talking to language models – chat, autonomous agents, tools, model serving, email, research, and more. Local-first, privacy-first, and no telemetry. Just you and your models.”
The interface is essentially designed as an all-in-one AI workspace where users can connect local models or external APIs, run autonomous AI agents, perform deep research tasks, compare multiple model outputs side by side, and manage documents directly inside the platform.
In the launch video, PewDiePie showcases the interface’s various features, demonstrating how it can handle research tasks, manage conversations, and operate as a private AI assistant without relying entirely on third-party services.
Despite all that, a major focus of the platform is privacy. Odysseus is marketed as a local-first experience, meaning users can keep their conversations, files, and personal data on hardware they control rather than sending everything to external servers.
The project is also completely open source and free to use. On the website, PewDiePie describes it as having “No sales team, no demo request, no Trojan horse,” while encouraging users to download, modify, and host it themselves.
That philosophy was summed up during the launch with one of the project’s most direct messages aimed at major AI companies: “The war on big tech has just begun.”
What makes it different from running ollama locally?
I got it up and running yesterday. You run ollama llms through it but it has some fun/useful tools like getting multiple models to give answers to the same question and voting on the correct answer.
Its more a quality-of-life thing, basically.
You’re not tied to ollama. You can choose other options like llama.cpp, vLLM, etc.
Indeed - I only used Ollama because I was already running it in my terminal.
His preteen followers don’t know how to do that.
Guy’s gotta stay relevant somehow.
What we need is less ai, not more.
So it’s just an alternative to Open WebUI and other AI GUIs? And I guess all that privacy talk is useless if you use non-local AI with it
I got the impression it was more like an in-between open webui and hermes/openclaw agents, or a hub with multiple tools, an all-in-one kinda thing.
Then again, I haven’t tried any of the things I mentioned, so take this with a grain of salt.
Yeah… sounds like something akin to AnythingLLM or LM Studio.
Or maybe there’s already a thousand of these things and one with a celebrity’s face on it feel’s icky?
This really just sounds like a web frontend for llm runners, its alright but to say its rivaling the big llm models is a biiiiig stretch. unless you have multiple cutting edge nvidia gpus at home, you arent gonna run anything close to the quality or context size of those big corporate models. a web frontend can only manage stuff and give you tools like those big llms. and there are lots of those already.
And like most of this LLM crap completely useless.
Fascinating how uttering the term “AI” can cause so many downvotes even when the system is just a harness that runs self hosted and can use completely openweight, even self trained models. Or maybe many on Lemmy just hate pewdiepie.
It’s probably both tbh
Does it just yell the N word any time you ask it a question?
