📺 screenpipe #004 | AI annotations, windows audio output, bug fixes
screenpipe #004
⬇️ download mac m app
⬇️ download windows app
give us a ⭐️(11.5k) to help the algorithm
hey louis & matt here
btw, in this newsletter, we share new features, bug fixes, work in progress, and what's next.
as a reminder, screenpipe is an open source library and an app to record data from your screens & mics and pass it into a llm. an ai powered by what you've seen, said, or heard:
✨ what's new
🏷️ AI tags (pipe store UI)
AI annotate you data continuously - in fact it's just a simple "pipe" from the "pipe store" (plugin system) that we just made available in the app interface!
what happen here? AI is adding tags to your data, every 1 min (using ollama and the latest microsoft AI model: phi3.5, locally) it will be useful to get better answers from AI - this is just an example of extending screenpipe through "pipes", you can also write your own very simply in Javascript (or TS)
we want to make it frictionless for you to create, share, use plugins that either enrich your data, analyse it, or anything else that get you the most out of screenpipe
to install:
(also available through CLI)
please DM louis to add your pipes to the store! (or send a PR it's OSS)
🔈 windows audio output
windows audio output is live! It means that even if you have headphones in a meeting the speaker will be recorded (make sure that screenpipe uses this device)
🔐 PII removal
this experimental feature removes things like credit card, or emails from the text extracted from your screen for more security
🪲 bug fixes
we fixed an issue on MacOS which was increasing memory usage (but it's still not 100% done, make sure to use restart interval 60 setting or more if you have issues
🧗♂️ known issues & workaround
- on macos you need to remove and re-add screen capture permissions every time you update the app (will solve this in upcoming days)
- windows defender may delete screenpipe, please tame it down! this is false positive
- linux screencapture does not support wayland (in a few weeks), use X
🔮 what's next
we're building what you want the most (check discord pinned message, we did a poll asking for it):
- better stability & performance
- better search, more relevancy
- add new OCR engine (esp. for linux)
- more recording customization (filtering in/out specific apps/tabs)
- advanced security: mp4 encryption at rest
- reduce storage required by half
- automatic audio device switch
- more productive UI (global shortcut, cursor-alike chat, shortcuts, etc.)
- easier to see your data from the app
- more customisable app AI settings (use your own openai api compatible URL)
btw we're running bunch of paid bounties (up to $200 atm) to make screenpipe even better, just go to github issues and check issues with label "bounty"
- the app is still in alpha and we've fixed tons of bugs, however, we're releasing daily updates to fix them, along with new features. we're a two-person team, but we have open source contributors joining, and we would be happy to welcome more! ☺️🙏
links
take care,
screenpipe
wanna chat?
You are receiving this email because you opted-in to receive updates from Mediar, Inc
Mediar, Inc, 2 Marina Blvd B300, San Francisco, CA 94123