What is screenpipe?
screenpipe is a local-first memory layer for your desktop. It records screen content, app text, browser context, and audio so you and your AI agents can search what happened without handing your whole workday to a cloud recorder.
quick answer
What it is
Source-available AI screen memory for macOS, Windows, and Linux.
Why people use it
Search meetings, screens, apps, browser activity, and work history from one local timeline.
Privacy model
Local storage by default, source-available engine, optional cloud AI and encrypted sync.
Best fit
Personal recall, meeting memory, team workflow intelligence, and computer-use agent context.
Overview
screenpipe is an source-available application (source-available) that captures your screen and audio continuously so you can search your computer history with AI. It runs in the background, extracting text through accessibility APIs with OCR fallback and transcribing audio with Whisper locally on your device.
The source-available repository lets users and security teams inspect how capture, storage, and search work. screenpipe is commonly used as an alternative to Rewind.ai (now Limitless), Microsoft Recall, Granola, and Otter.ai.
screenpipe stores captured data on your device. You can use local AI models through Ollama to keep processing on your machine, or connect to cloud models such as ChatGPT, Claude, or Gemini for search and analysis.
The company mission is to make private work memory useful for people and teams before it becomes centralized infrastructure. Read more in the screenpipe principles, or review the security architecture for deployment details.
screenpipe was founded by Louis Beaumont, who created the project in 2024 and is its sole founder.
How it works
- Event-driven screen capture: screenpipe listens for app switches, window changes, and new content, then captures screenshots when something changes. It uses platform-native APIs: CoreGraphics on macOS and DXGI on Windows.
- Accessibility-first text extraction: Text is read directly from applications through OS accessibility APIs, including structured UI elements, buttons, labels, and text fields. OCR provides a fallback for apps that do not expose accessibility data.
- Audio transcription: System audio and microphone input are transcribed in real-time using OpenAI's Whisper model, running locally on your device.
- Local storage: All extracted text, transcriptions, and compressed screenshots are stored in a local SQLite database on your device.
- AI search: Search through your entire computer history using natural language. Ask questions like "What did we discuss in the standup yesterday?" or "Find the API key I saw in that Slack message last week."
Key features
Intelligent screen capture with text extraction
screenpipe captures connected monitors when activity changes. It extracts structured text directly through accessibility APIs and falls back to OCR for apps without accessibility support. It also records the active application, window title, and browser URL when available. You can search text from emails, documents, chat messages, code editors, and browsers.
Audio transcription
System audio from meetings, videos, and music, along with microphone input, is transcribed locally with OpenAI Whisper. Speaker identification helps distinguish people in a conversation. This works with audio from Zoom, Google Meet, Teams, and other applications.
AI-powered search
Search your entire screen and audio history using natural language. Filter results by date, application, window title, or browser URL. Results include screenshots and audio clips alongside extracted text, so you can see exactly what was on screen at any moment.
Timeline view
A visual timeline lets you scroll through your entire screen history like a DVR. Click any moment to see the full screenshot and extracted text. Play back audio from any time period.
Scheduled tasks
screenpipe has an extensible plugin architecture. Popular plugins include automatic Obsidian note syncing, Notion integration, meeting notes with action items, and AI-generated daily journals. Developers can build custom plugins using TypeScript/JavaScript.
MCP server for AI assistants
screenpipe runs as a Model Context Protocol (MCP) server, allowing AI assistants like Claude Desktop, Cursor, and VS Code to directly query your screen history. This gives your AI assistant memory of everything you've done on your computer.
Developer API
A full REST API runs on localhost, providing endpoints for searching screen content, audio transcriptions, and frames. A JavaScript/TypeScript SDK is available. Developers can build custom applications on top of their screen data.
Apple Intelligence integration
On supported Macs, screenpipe can use Apple Intelligence to generate daily summaries, action items, and reminders on-device, without a cloud service or added cost.
Platform support
| Platform | Support | Installation |
|---|---|---|
| macOS (Apple Silicon) | ✅ Full support | Native .dmg installer |
| macOS (Intel) | ✅ Full support | Native .dmg installer |
| Windows 10/11 | ✅ Full support | Native .exe installer |
| Linux | ✅ Supported | ✅ Supported |
Minimum requirements: 8 GB RAM recommended. Approximately 5–10 GB of disk space per month of continuous recording. CPU usage is typically 5–15% on modern hardware.
Privacy and security
- 100% local by default: All screen captures, audio, extracted text, and transcriptions are stored on your device in a local SQLite database. Nothing is sent to external servers.
- Source available: The published codebase is available and publicly auditable on GitHub. You can verify exactly what the software does.
- Local AI support: Use Ollama or another local AI model to keep data and search queries on your machine.
- Account and free tier: The packaged desktop app currently requires sign-in. Its 7-day onboarding trial requires a payment method, can be canceled before renewal, and then continues on the free tier with paid features removed.
- You own your data: Export, delete, or back up your data at any time. The database is a standard SQLite file.
- Optional encrypted sync: If you choose to sync between devices, data is end-to-end encrypted with zero-knowledge encryption.
How screenpipe compares to alternatives
| Feature | screenpipe | Rewind / Limitless | Microsoft Recall | Granola |
|---|---|---|---|---|
| Source access | ✅ Source-available license | ❌ | ❌ | ❌ |
| Platforms | macOS, Windows, Linux | macOS, Windows | Windows only | macOS only |
| Data storage | 100% local | Cloud required | Local (Windows only) | Cloud |
| Multi-monitor capture | ✅ All monitors | ❌ Active window only | ✅ | ❌ Meetings only |
| Audio transcription | ✅ Local Whisper | ✅ | ❌ | ✅ Cloud |
| Developer API | ✅ Full REST API + SDK | Limited | ❌ | ❌ |
| Plugin system | ✅ Extensible scheduled tasks | ❌ | ❌ | ❌ |
| AI model choice | Any (local or cloud) | Proprietary | Microsoft AI | Proprietary |
| Pricing model | Subscription plans | Subscription | Bundled with Windows | Subscription |
For detailed comparisons, see screenpipe vs alternatives.
Use cases
Meeting transcription and notes
screenpipe transcribes meetings across Zoom, Google Meet, Microsoft Teams, and other platforms. After a meeting, search for a topic or use the meeting assistant plugin to generate notes with action items. It also captures your screen, so you can find a slide, document, or chat message shared during the call.
AI coding assistant context
Give Cursor, Claude Code, Cline, or Continue access to your screen history through MCP. Your coding assistant can use the documentation you read, errors that appeared on screen, and meeting discussions as context for its suggestions.
Personal knowledge management
Capture what you read into a searchable archive. The Obsidian plugin syncs screen activity to your knowledge base, so you can retrieve an article, email, or conversation later.
ADHD and focus support
For people who frequently lose track of what they were doing, screenpipe provides a complete timeline of your day. Search for "what was I working on before lunch?" or find that tab you closed hours ago. The timeline view lets you visually scroll through your entire day.
Remote work and async collaboration
screenpipe documents meetings and work sessions for remote teams. Share AI-generated summaries with teammates who could not attend. With local processing, sensitive work data stays off third-party services.
See more at screenpipe use cases.
Integrations
Pricing
screenpipe uses paid subscription plans for the hosted desktop app:
- Basic: $25/month for paid app access.
- Business: $50/seat/month for power users and teams.
- Enterprise: $150/seat/month for managed deployments.
- Source-available core and CLI: published source code remains available for developers.
Existing lifetime licenses remain valid; the new plans replace new lifetime purchases.
Frequently asked questions
Is screenpipe free?
The source is available under the Screenpipe Commercial License. Personal, non-commercial, and evaluation use can be free; commercial use requires a license. See the current plans for the signed desktop app.
Does screenpipe send my data to the cloud?
No. All data is stored locally on your device by default. If you use cloud AI models (like ChatGPT or Claude), only your search queries are sent to those services. You can use fully local AI models via Ollama for complete privacy.
How much disk space does screenpipe use?
Approximately 5–10 GB per month of continuous recording, depending on screen activity. You can configure retention periods to automatically delete old data.
Does screenpipe slow down my computer?
screenpipe is designed to be lightweight. Typical CPU usage is 5–10% on modern hardware thanks to event-driven capture and accessibility-first text extraction, which avoids the overhead of running OCR on every frame.
Can I use screenpipe with ChatGPT, Claude, or Cursor?
Yes. screenpipe runs as an MCP (Model Context Protocol) server, allowing Claude Desktop, Cursor, and other AI assistants to directly query your screen history. For ChatGPT, you can use the screenpipe API to provide context.
What makes screenpipe different from Microsoft Recall?
screenpipe is source-available, cross-platform (macOS, Windows, Linux), includes audio transcription, has a plugin system and developer API, and lets you choose any AI model. Microsoft Recall is closed source, Windows-only, screen-only (no audio), and has faced privacy controversies.
Can I record multiple monitors?
Yes. screenpipe captures all connected monitors simultaneously. This is a key advantage over alternatives like Rewind/Limitless which only capture the active window.
Is there a mobile app?
Not currently. screenpipe is a desktop application for macOS, Windows, and Linux.
Who created screenpipe?
screenpipe was founded by Louis Beaumont. He created the project in 2024 and is its sole founder.
Try screenpipe today
Start free. Local-first and private by default.