📺 screenpipe #003 | pipe store, dev mode, MacOS audio output, new AI for audio
screenpipe #003
⬇️ 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 OSS library and an app to extract data from your screen & audio and pass it into a llm. an ai powered by what you've seen, said, or heard:
✨ what's new
🔈 MacOS audio output
MacOS audio output is live! (for non-beta MacOS versions) (fyi "Display 1 (output)" is usually your mac speaker despite the non-intuitive name) you can now customize the recording settings in the app, soon you would be able to choose which monitor/app/tab to record or to ignore:
🔍 search improvements
new search by app names and tabs, e.g. you can query your Discord history
🔄 auto-updater & pipe store
we released the app auto-updater, it will show a dialog when reloading the app we officially released the pipe store! it's only for dev right now, you can use it like this:
- write a JS or TS plugin that will process your local data using AI
- write the results to a file, or anywhere (Notion, X, Salesforce, etc.)
this is how you can use pipes through CLI:
here's our first pipe, which summarizes your days using Ollama 24/7:
you can find it in our GitHub repo examples directory, it's one line of code to get started :). eager to hear your ideas of pipes we could ship (or yours!)
why? we want to make it effortless for you to create, share, use pipes that get the most out of your data, we're inspired by the Obsidian plugin store
🪲 bug fixes
- issues with Ollama/ai prompt in the app
- less crashes when computer sleeps
- duplicate screenpipe processes
- cleaner, faster search
🔮 what's next
- Windows audio output (we just bought a laptop for it!), fyi we created a $100 bounty for anyone that would implement it (check github issues)
- pipe store UI - create, share, use plugins in seconds
- improved search, indices, vector search, more customization & filtering out specific apps, windows, PII removal, encryption
- storage optimization
- reduced compute and operating memory usage
- easier to see your data from the app
- more stability in the app
- automatic audio device switch
- more productive UI (global shortcut, cursor-alike chat, shortcuts, etc.)
- compute offloading (e.g. run transcription and OCR on your own server)
- 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