screenpipe
by: mediar-ai
AI app store powered by 24/7 desktop history. open source | 100% local | dev friendly | 24/7 screen, mic recording
📌Overview
Purpose: ScreenPipe aims to revolutionize AI application development by providing an open-source framework that records desktop activity locally and in real-time, allowing developers to create context-aware applications.
Overview: ScreenPipe is a desktop application framework that continuously records user interactions with their computer to provide AI developers with rich contextual data. This enables the development of innovative applications tailored to user behavior and preferences, all while maintaining local data privacy.
Key Features:
-
24/7 Local Recording: Continuously captures screen activity and audio, ensuring a comprehensive dataset without reliance on cloud storage, thus enhancing data privacy.
-
Easy Plugin Creation: Developers can create custom "pipes" (plugins) using a supported framework, enabling them to build and monetize tailored applications with minimal effort.
ScreenPipe
Overview
ScreenPipe is an AI app store powered by 24/7 desktop history. It is open source, 100% local, and developer-friendly, with continuous screen and microphone recording.
Slogan
"Recording reality, one pixel at a time"
Download
News
- 2025/03: Introducing the ScreenPipe Operator: A low-level API, 100% accurate without unreliable pixel-based agents.
- 2025/02: Hackathon with $12k in cash prizes on 28 Feb.
- 2025/01: Partnering with Different AI for financial automations and a drop-in replacement for Obsidian.
- 2024/12: Stripe integration for developers to earn income via pipe store.
- 2024/11: ScreenPipe is the number 1 GitHub trending repo.
- 2024/10: Backed by Founders, Inc.
- 2024/09: Featured on Hacker News.
- 2024/08: Users can now create, share, and install plugins from the app.
- 2024/08: Running bounties for contributions.
- 2024/08: Released Apple & Windows Native OCR.
- 2024/07: Launched the desktop app.
How It Works
- Records everything 24/7, 100% locally, using minimal resources.
- Indexes data into an API for developers to build AI apps utilizing user context.
Get Started
For macOS or Linux:
curl -fsSL get.screenpi.pe/cli | sh
For Windows:
iwr get.screenpi.pe/cli.ps1 | iex
Then run:
screenpipe
Make sure to allow permissions on macOS (screen, mic).
Create Plugins
ScreenPipe has a plugin system called "pipe." To create a plugin:
bunx --bun @screenpipe/dev@latest pipe create
Publish your plugin to earn:
cd foo
bunx --bun @screenpipe/dev@latest pipe register --name foo [--paid --price 50] # For subscription
bun run build
bunx --bun @screenpipe/dev@latest pipe publish --name foo
Community Links
Contributing
Contributions are welcome! Please see the CONTRIBUTING.md for more.