Question 1

What is screenpipe?

Accepted Answer

screenpipe is AI agent memory: it continuously captures what you've seen, said, and heard on your computer, and gives that context to whatever AI you already use, so it never starts from scratch. It runs on macOS, Windows, and Linux, and exposes your history to any AI through a local API and MCP server.

Question 2

What will screenpipe actually remember?

Accepted Answer

screenpipe builds a timestamped, searchable history from on-screen text, app and window context, screen images, system audio, and microphone audio you choose to capture. Use it to find something you saw, reconstruct a day, recover a decision, or draft a follow-up. It cannot recall a period that was not successfully captured.

Question 3

Do my screen recordings and audio leave my computer?

Accepted Answer

By default, capture, transcripts, and the search index stay on your device. Data leaves only when a feature you enable needs it, for example cloud AI, cloud sync, an export, a connector, or a team workflow. Each integration has its own destination: local-first does not mean every optional feature runs locally.

Question 4

Can I exclude sensitive apps, windows, or hours?

Accepted Answer

Yes. You can pause recording, use recording schedules, include or ignore apps and windows, ignore URLs, and set automatic retention. Privacy filters can redact sensitive text before it is stored, and DRM-protected content pauses capture by default. Review these settings before recording confidential work.

Question 5

What should I expect from CPU, battery, and storage use?

Accepted Answer

Any always-on capture uses CPU, battery, and disk. The load depends on your displays, capture quality, audio sources, and local transcription settings. screenpipe uses accessibility events, GPU capture, power tiers, compression, and retention controls to reduce that cost, but it is not zero. If the timeline has gaps, fix capture first. An AI summary cannot recover missing data.

Question 6

Where can I run it, and can I inspect the code?

Accepted Answer

screenpipe runs on macOS, Windows, and Linux. Its capture engine is public and source-available under the Screenpipe Commercial License, so you can inspect the code that handles your data, build it yourself, or run the CLI headless.

Question 7

How much does screenpipe cost?

Accepted Answer

There is a free tier for trying local capture, AI search, and meeting notes. Paid plans add more history, AI usage, model choices, sync, and team controls. Check the pricing page for the current price, trial, limits, amount due today, and renewal terms before checkout; existing lifetime licenses keep working.

Question 8

What should I do first after installing?

Accepted Answer

First, confirm that the timeline contains recent screen and audio history. Then retrieve one specific fact from the last hour, such as “what did I decide about the launch, and where did I say it?” Only connect a note, CRM, or other destination after that result is useful. This catches permission, capture, transcription, and search problems before they become unreliable automation.

Question 9

Can Claude, Codex, or my own agent use this history?

Accepted Answer

Yes. MCP-compatible agents can query screenpipe, and developers can use the local REST API, SDK, CLI, or SQLite database. A connected agent gets the context it requests and your settings permit; screenpipe does not automatically send your entire archive with every prompt.

Question 10

Can screenpipe turn repeated work into follow-ups or SOPs?

Accepted Answer

Yes, but start with a reviewed draft. screenpipe can use your captured work to prepare a meeting follow-up, daily or weekly review, or a draft SOP from repeated steps. Once the output is trustworthy, run it on a schedule or trigger. Keep external writes and sends behind approval until the workflow has earned that trust.

Question 11

Is screenpipe mainly a meeting recorder?

Accepted Answer

No. Meetings are one useful source, but screenpipe also connects them to the documents, browser research, messages, code, and decisions around them. If you only need polished call transcripts, a meeting-only tool may be simpler. Use screenpipe when recall and follow-through span multiple apps and hours or days.

Question 12

Can a company deploy it without centralizing everyone's raw history?

Accepted Answer

Yes. Enterprise supports managed deployment, SSO/SAML, device policies, and team workflows while capture remains local-first on each endpoint by default. Central search or storage is configured explicitly, not implied by deployment. A rollout still needs employee consent, clear policy, and review of applicable recording laws; screenpipe should not be used for covert employee surveillance.

Your computer history.Open to any AI.

See real work become reusable context.

Ask AI what actually happened at work.

Watch your agents work in the background.

One history layer across every model and operating system.

Keep your history portable

Remember more than events

Watch agents do the follow-up

Use the apps you already have

Keep sensitive work out

Roll it out across the company

Build your workflow memory.

Questions people actually ask

Straight answers about capture, privacy, reliability, and getting useful work back.

the product

getting useful work back

for teams