MCP ExplorerExplorer

Screenpipe

@mediar-aion 17 days ago
14973 MIT
FreeCommunity
AI Systems
#ai#computer-vision#llm#machine-learning#ml#multimodal#vision#agents#agi
AI app store powered by 24/7 desktop history. open source | 100% local | dev friendly | 24/7 screen, mic recording

Overview

What is Screenpipe

Screenpipe is an AI app store that operates 24/7, powered by continuous desktop history recording. It is open source, fully local, and developer-friendly, providing features like screen and microphone recording.

Use cases

Use cases for Screenpipe include creating tutorials, recording gameplay, conducting user experience research, and developing AI applications that require real-time data from desktop interactions.

How to use

To use Screenpipe, download the desktop application from the official website, install it, and start recording your screen and microphone. You can access various AI applications through the app store interface.

Key features

Key features of Screenpipe include open-source accessibility, 100% local data processing, developer-friendly environment, and continuous recording of screen and microphone.

Where to use

Screenpipe can be used in various fields such as software development, content creation, online education, and any area where continuous monitoring and recording of desktop activity is beneficial.

Content

English | 简体中文 | 日本語

logo

mediar-ai%2Fscreenpipe | Trendshift

[ screenpipe ]

AI app store powered by 24/7 desktop history

open source | 100% local | dev friendly | 24/7 screen, mic recording

[ recording reality, one pixel at a time ]

Download the Desktop App

YouTube Channel Subscribers

Join us on Discord X account Rewarded Bounties Open Bounties

Screenshot 2025-02-15 at 7 51 18 PM

image

https://github.com/user-attachments/assets/628c6c01-a580-4b21-bce9-3e7b186914a4

https://github.com/user-attachments/assets/973ee8e5-5240-4d36-83fe-d38c53efe6a9


news 🔥


how it works?

  • we record everything 24/7, 100% locally, uses 10% CPU, 4 GB ram, 15 gb/m
  • we index it into an api
  • dev build ai apps w user’s full context, desktop native, nextjs, publish, monetize

why?

  • ai models are commoditized
  • ai is as good as its context
  • the most valuable context is all contained in your screen

get started

macos, linux:

curl -fsSL get.screenpi.pe/cli | sh

or on windows

iwr get.screenpi.pe/cli.ps1 | iex

then

screenpipe

make sure to allow permissions on macos (screen, mic)

create plugins

bunx --bun @screenpipe/dev@latest pipe create

screenpipe has a plugin system called “pipe” which lets you create desktop app in nextjs in a sandboxed environment within our Rust code, read more

you can then publish these to our store and make money:

cd foo
bunx --bun @screenpipe/dev@latest pipe register --name foo [--paid --price 50] # subscription
bun run build
bunx --bun @screenpipe/dev@latest pipe publish --name foo

community

star history

Star History Nov 24 2024

contributing

contributions are welcome! if you’d like to contribute, please read CONTRIBUTING.md.

Rewarded Bounties Open Bounties

Tools

No tools

Comments