📺 screenpipe #10 | autocompletion anywhere on your computer, 6x faster transcriptions
screenpipe #010
⬇️ download mac m app
⬇️ download windows app
give us a ⭐️(11.5k) to help the algorithm
we keep growing, thank you for your support
hey everyone, matt and louis here
btw, in this newsletter we share new features, bug fixes, works in progress, and what's next. say hi to us: louis, sf timezone matt, sf timezone
✨ Highlights
✌️ autocomplete shortcut "//" in beta
the autocomplete feature is so useful. it leverages the history of your computer to provide a relevant response, as shown in the demo. i'm responding to the user's post. the LLM knows that i'm the founder of screenpipe, so it responds accordingly. take a look
when i need to write a message/email, i want an LLM to help me create the first draft, but the LLM doesn't have context about the conversation or what i personally know. screenpipe lets you use a shortcut "//".
how does it work?
- it extracts all the content from the current window/conversation
- searches your screen data history to find relevant context
- passes everything together to the LLM to draft a response
another demo: https://youtube.com/shorts/O28f9z0aZVk
available here: https://discord.gg/HswKWBjaxe
📖 screen time storyteller pipe
a new pipe called "Screen Time Storyteller" for Screenpipe. The pipe analyzes user's 24/7 screen recordings and generates personalized, humorous roasts about their digital habits. It aims to provide insights and motivation for improving productivity through AI-powered feedback.
⭐️ other things
- chinese support (OCR, huggingface mirror to download models)
- better OCR on macos
- fix: windows video rendering in the UI
- wayland 99% done
- new updater system
🚀 ongoing
- embed a llama3.2 in your app (no need to install Ollama)
- accessibility API to get source of UI data in addition to OCR
- https://github.com/mediar-ai/screenpipe/pull/443 (new pipe)
- windows arm support
- faster inference on cpu using mkl
- reduced windows installer size of 70 mb
- support for newly released openai whisper large turbo 6x faster
🌆 b2b use cases
- fill out jira tickets on autopilot based on your screen data
- write engineering documentation based on your daily work in IDE
- record how employees perform certain tasks for internal coaching best practices
🙏 ask
hey, your feedback and support are super valuable to us, hit the reply button and tell us what you'd like to see in screenpipe.
like screenpipe? mention it online, it would help us grow! 🚀
you can tag screen_pipe on x and we will retweet you ❤️
- 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, and we would be happy to welcome more of them! ☺️🙏
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