cloaWhat we’re thinking about.
Ideas on AI that actually helps — proactive, personal, and always learning.
agentic AI just went mainstream. here's what the first big moment taught us.
Open-source AI agents hit 180,000 GitHub stars in a month. Then some real incidents happened. Here's what the community learned and how we think about building personal AI responsibly.
your AI just deleted something. there's no undo.
Autonomous AI agents are powerful enough to act on your behalf. They can also delete, send, and publish things you can't take back. Here's how that happens and what good AI design does about it.
what if your AI woke up before you did?
Most AI waits for you to ask. Cloa checks your calendar, resolves conflicts, and preps your day before your alarm goes off. This is proactive AI.
local-first vs cloud AI: what privacy actually means
Running your AI on your own server sounds like the private option. But privacy is more complicated than where data lives. Here's how we think about it and why we made the choices we did.
an AI that actually remembers you
You told it once. Weeks later, it remembered. Cloa uses long-term memory to recall your preferences, relationships, and context so you never repeat yourself.
automate your life, not your code
Set up automated workflows in plain English. Cloa connects your calendar, email, Notion, Slack, and Telegram and runs them on schedule without code.
your data, your rules
Every Cloa integration has granular permissions: off, confirm, or full auto. You control exactly what your AI can access, read, and act on.
the future of personal AI isn't a chatbot
We don't need smarter chatbots. The future of personal AI is an agent that knows you, acts for you, and shows up wherever you are across app, voice, and messaging.
Ready to meet your AI?