Let AI update itself.
Familiar watches you work so your AI can create its own skills and update its knowledge. Free, open source, local, and offline.
Install Familiar, then ask your existing AI:
How does it work?
8:41 AM
9:17 AM
10:03 AM
10:52 AM
12:04 PM
1:38 PM
3:15 PM
4:49 PM
5:33 PM
6:22 PM
8:41 AM
9:17 AM
10:03 AM
10:52 AM
12:04 PM
1:38 PM
3:15 PM
4:49 PM
5:33 PM
6:22 PM
Familiar looks at your screen every few seconds and converts it to text using Apple's native OCR.
It also saves everything that passes through your clipboard (this includes most third-party speech-to-text tools, too).
Your existing AI gets a new skill and a lot more context.
That's it. We kept it simple.
Just a menu bar icon, so you can pause or quit anytime. As you use your existing AI agent, it can use that context to help you. To make that smooth, Familiar can auto-add a Skill — a text file that tells your AI when and how to use your new folder.
We've observed AI agents use Familiar as one more layer on top of tools, file system, skills, and the LLM's own knowledge. Context compounds: each source fills the blind spots of the others, and the AI starts connecting dots none of them could surface alone.
This scares the crap out of me.
It scares us, too.
Tal started his career at DuckDuckGo and Maxim is ex-Orca Security and an early contributor to OpenClaw. We knew that for this to work, it would have to be:
Free.
Local.
Open source.
Offline.
Running locally and offline makes Familiar the security equivalent of “taking a screenshot and saving it to your hard drive.” From there, it's your (or your company's) AI provider of choice.
Working with financial info? Googled something embarrassing?
You can pause or quit Familiar anytime. Forgot to pause? You can also delete recent captures.
Copying and pasting passwords and API keys?
Familiar skips passwords, tokens, and API keys. To be extra safe, you can delete recent captures.
Rightfully Asked Questions
/familiar use cases
“What happens if someone leaves tomorrow?”
What did I do today that I should document for my team?
What unwritten rules are worth adding to our operating manual?
I’m onboarding a new team member — what should I tell them?
“We should be further along with AI”
What should I have delegated to AI today?
Turn what I did today into Skills for AI.
What customer interactions are worth adding to our support agent instructions?
What updates should I make to my second brain?
“How can I make my team more self-reliant?”
I just had a breakthrough solving a problem. Reconstruct the exact sequence so I can document it.
I’m going on parental leave. Based on my last 3 months, what does my replacement need to know about each initiative?
What did I do today that can be delegated?
“Am I spending my time on the right things?”
Given everything on my plate, what should I cut or delegate?
When does my deep work actually happen, and what kills it?
Write my weekly status update based on what I actually did this week.
It’s performance review time. Write my brag document from the last 6 months.
“Why did we decide that?”
The VP asked “didn’t we already decide this?” and I know we did but I can’t find it.
What decisions did I make today and what was my reasoning?
Help me run an honest retrospective.
“Who’s falling off my radar?”
Who am I not talking to enough?
Before my call with X next week, show me everything I’ve seen or read about them recently.
What’s every interaction I’ve had with Bob in the last month?
We can't imagine working without AI sitting next to us.
We know that's a weird sentence, but AI needs wayyyyyy more context that lives outside our past chats or MCP integrations. No human can watch my screen all day, remember everything, and provide piercing answers on demand. For any amount of money.