Hey! Tal here. Maxim and I created Familiar to capture our screen (and clipboard) every few seconds and save it as markdown. That way our local agent can use that as context (through a cron, skill, or slash command).
Our early testers are showing us how to use it:
- Update Claude's skills/memory based on their workday (in a scheduled task/heartbeat)
- Typing "help me with what I'm working on right now" without having to prompt/describe
- Enriching meeting transcripts with what was actually on screen (and vice versa)
- Forking it into their coaching app so coaches can see what learners did between sessions
- Someone new to tech used Familiar during a trial week at a YC startup, so that AI could coach him every few hours (and got the job)
We've consistently seen AI use Familiar context like a "router" layer. Recently, my agent "saw" that I spent a long time on a document, so it fetched the full doc directly. We've also seen the agent traverse the markdown, then decide to fetch the original image (so cool).
Familiar uses Apple's native OCR, deletes screenshot images after 48 hours, and redacts passwords/credit card numbers/SSNs/API tokens/etc. We'd love contributions on what else to block: https://github.com/familiar-software/familiar/tree/main/src/... or in general ways to improve privacy.
We stand on the shoulders of giants: screenpipe, rewind, dayflow, etc. Since then: 1) Local agents got good at handling massive amounts of messy text files 2) Local agents have their own memory and skills systems
Familiar is our "bitter lesson" version: just hand over context and get out of the way. The right way to do that piece is open source/free/offline.
Definitely possible. And you guessed it - American.
Is health insurance the only thing to worry about? Any other reasons to save up a lot of money, or something to insure for?
For example, if a medical issue arises, insurance covers treatment, but if it's now difficult to sustain myself, am I now dependent on unemployment/social services (or savings)?
I lead a minimalist/nomadic lifestyle now, and always wondering if at some point the music has to stop and I have to integrate into the system as I get older (any kids, family aside).
That part I'm sold on. I'm wondering about, as another comment mentioned, what happens if you discover one day you're not self sufficient, even temporarily (significant illness, chronic illness, major injury - or something I'm not considering). If I don't want to be a burden on anyone on the grid, but don't want to depend on social services, how do I factor that in?
The comments here are really thought provoking. I feel like I'm missing something - is there some kind of unmentioned catch, like don't get sick, or you have to have really good workers/health/disability insurance - to make this work safely long term?
I love the contrarian thinking but want to make sure I'm accounting for legitimate cases my young mind might not conceive of. Or am I overthinking it?
Our early testers are showing us how to use it:
- Update Claude's skills/memory based on their workday (in a scheduled task/heartbeat)
- Typing "help me with what I'm working on right now" without having to prompt/describe
- Enriching meeting transcripts with what was actually on screen (and vice versa)
- Forking it into their coaching app so coaches can see what learners did between sessions
- Someone new to tech used Familiar during a trial week at a YC startup, so that AI could coach him every few hours (and got the job)
We've consistently seen AI use Familiar context like a "router" layer. Recently, my agent "saw" that I spent a long time on a document, so it fetched the full doc directly. We've also seen the agent traverse the markdown, then decide to fetch the original image (so cool).
Familiar uses Apple's native OCR, deletes screenshot images after 48 hours, and redacts passwords/credit card numbers/SSNs/API tokens/etc. We'd love contributions on what else to block: https://github.com/familiar-software/familiar/tree/main/src/... or in general ways to improve privacy.
We stand on the shoulders of giants: screenpipe, rewind, dayflow, etc. Since then: 1) Local agents got good at handling massive amounts of messy text files 2) Local agents have their own memory and skills systems
Familiar is our "bitter lesson" version: just hand over context and get out of the way. The right way to do that piece is open source/free/offline.