people seem to like this
Sharing an internal infra product we built:
• 8 vCPUs, 2GB RAM, 50GB SSD
• Autoscales to 64GB RAM as needed
• $20/month flat, billed by the second
• Limited supply, max 8 per user
• Web app, SSH, CLI
→ proton.computer
Cube Computer retweeted
One machine with all your tools, automatically scaling with your workflows and needs.
just an fyi that cube.computer now installs and runs leading open-source agentic apps like
• @t3dotcodes
• @papercliping
• @OpenMausBot
and your own web apps if you add a `cube.json` manifest
cube apps are just repos with a `cube.json` manifest. install or generate your own.
three by @Paul_Rony are in the market:
• notes app you share with your agents
• radar app for scanning social media
• video renderer for vibing bangers
→ cube.computer
The Cube app market is now GA on cube.computer. Install @OpenMausBot and you get an open-source Grok Bot on a cloud machine you fully control.
RT @yiliush: Cube apps are now GA on cube.computer. Run @telepathinc's television.run on your Cube cloud machine so it a…
Cube apps are now GA on cube.computer. Run @t3dotcodes on your Cube so your agents can build 24/7 on a cloud machine you fully control.
you can run @OpenMausBot on your @cubecomputer_ and you get the same UX as all these locked-in agent products on a virtual machine you own, can install other apps and agents on, can migrate or delete.
there’s something quite awkward about all the personal agents in the current hype cycle
muse, grok bot, instinct, dots, and whatever google, anthropic will come up with
none of them is “mine”
i’d be trusting a vendor for some of the most sensitive data about me and bet on them handling it with extreme responsibility. what if they have a data leakage incident? what if they hired a wrong employee? what if they simply break bad?
i’d also be betting on their model. right now i’ve set up a lot of my stuff in grok bot, but what if their model falls behind? what if another model becomes 10x better on pure intelligence? then i’ll either miss out on a better assistant, or have to bite the bullet and do a full migration
i’d also have to bet on their product. they may not build the features i want. they may not allow me to customize enough. and one day my assistant may show me ads
that feels like way too much betting than what i’d be comfortable with, if i truly want literally everything in my life to go through and be taken care of by an assistant
with all that considered, i’m more bullish on open source personal agents that run on people’s own computers. but i think these open source projects have to break out of the assumption that their users are developers and they can just throw a repo at them and ask them to launch a terminal
a well polished, fool proof, community maintained, vendor agnostic, free personal agent that everyone can run by themselves without locking into a SaaS - that’s what i think many people will need
duuude T3 just running directly on my cube.computer but used via our local client with zero setup
sunday experiment: one-click install of open-source agentic apps like @telepathinc's television or @OpenMausBot on @cubecomputer_ and holy shit... it just works and feels effing amazing
sunday experiment: one-click install of open-source agentic apps like @telepathinc's television or @OpenMausBot on @cubecomputer_ and holy shit... it just works and feels effing amazing
one-click github repo access on cube.computer
please for the love of all that is holy just use @cubecomputer_
get up and clauding in cube.computer in two minutes




















