Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.screenpi.pe/llms.txt

Use this file to discover all available pages before exploring further.

screenpipe captures your screen and audio 24/7 and makes it available to AI. here’s everything you can do with it, organized by what you’re trying to accomplish.

​
choose your first workflow

screenpipe gets more useful when you give it a concrete job. start with one workflow, one person, and one week of evidence.
if you are…start withsuccess looks like
individual founder or operatordaily recap plus open-loops summaryyou can ask “what did I do today?” and get useful next steps
developer using Claude, Codex, or CursorMCP memory for recent terminal, browser, and meeting contextyour AI can recover what you were doing before context loss
team leadSOP capture for one repeated workflowone clean process doc from real screen activity
sales or customer successmeeting summary plus follow-up drafttranscript, screen context, objections, and next email in one place
enterprise pilotone or two test machines, one repeated workflow, clear privacy filtersadmin can see device status and the pilot user gets a useful output
the best first prompt is usually: 
Search the last 24 hours of screenpipe data.
Summarize what mattered.
Include:
- work completed
- meetings and decisions
- blockers
- open loops
- suggested next actions

​
close your loops

you jump between 10 projects a day. you forget where you left off. screenpipe remembers for you.
  • ask AI: “what was I working on before lunch?” → get the exact file, app, and context
  • ask AI: “what was that API endpoint I was looking at in Chrome yesterday?” → find it instantly
  • run Day Recap pipe: get a daily summary of accomplishments, unfinished work, and what to do next
  • search by time: curl "http://localhost:3030/search?start_time=2026-04-10T09:00:00Z&end_time=2026-04-10T12:00:00Z"
best setup: connect Claude Desktop or Cursor via MCP → ask natural language questions about your screen history.

​
turn real work into SOPs

support, finance, operations, and QA workflows are often trapped in someone’s hands. screenpipe turns one good run into a draft process.
  • record one clean pass: open the same tools you normally use and complete the workflow once
  • ask for a step-by-step SOP: include systems used, decisions, exceptions, and evidence links
  • review with a teammate: mark anything the AI guessed or missed
  • turn it into a pipe: run the same summary after each repeated workflow
example prompt: 
Search the last 60 minutes of screenpipe data.
Create a training doc for a new teammate.
Use the screen text, transcript, app names, and timeline moments.
Flag any step that needs human verification.
best setup: desktop app + audio recording + MCP or a custom pipe.

​
never miss a meeting detail

someone mentioned a deadline in a Zoom call but you weren’t paying attention. screenpipe was.
  • search transcriptions: “what did John say about the deadline?” → find the exact quote
  • install Meeting Intelligence pipe (17 installs): AI summaries enriched with relationship history, screen context, and memories — gets smarter over time
  • speaker identification: screenpipe identifies who said what — label speakers once, recognized forever
  • search by speaker: curl "http://localhost:3030/search?content_type=audio&speaker_name=John"
best setup: enable audio recording in settings → install Meeting Intelligence from the pipe store.

​
track your time automatically

you switch between coding, emails, meetings, and slack all day. screenpipe tracks where your time actually goes.
  • run Time Breakdown pipe: see exactly how many hours you spent in each app
  • install Toggl Time Tracker pipe (17 installs): auto-log time entries based on active apps — no manual tracking
  • productivity score: pipes can calculate focused work time vs. context-switching time
  • by project: AI groups related activities into projects automatically
best setup: install Toggl Time Tracker from the pipe store for automatic tracking, or run Time Breakdown for on-demand analysis.

​
write standups and reports in seconds

your team uses daily standups. screenpipe writes them for you based on what you actually did.
  • run Standup Update pipe: generates “what I did / what I’m doing / blockers” in under 150 words
  • weekly reports: create a custom pipe that summarizes your week
  • share with team: copy-paste the output into Slack, Teams, or Discord
best setup: go to Pipes in the sidebar → install Standup Update → run it every morning before standup.

​
build a personal knowledge base

everything you’ve ever seen on your screen, searchable forever.
  • install Digital Clone pipe (574 installs, most popular): saves and maintains memories of who you are — builds a persistent AI memory
  • install Obsidian Daily Summary pipe (62 installs): writes daily summaries directly into your Obsidian vault
  • install AI Prompt Journal pipe: capture every prompt you send to ChatGPT, Claude, etc.
  • sync iMessages (18 installs), Voice Memos (15 installs), Apple Photos (4 installs) into screenpipe
  • search by app, URL, time range, or speaker: find anything you’ve ever seen or heard
best setup: install Digital Clone + Obsidian Daily Summary from the pipe store.

​
give AI memory of your screen

LLMs are stateless — they don’t know what you were working on 5 minutes ago. screenpipe fixes that.
  • Claude Desktop: ask “what was I working on?” and Claude searches your screen history via MCP
  • Cursor: give Cursor context about what you’ve been coding, what PRs you reviewed, what errors you saw
  • Claude Code: search your screen history from the terminal
  • ChatGPT: use your ChatGPT subscription inside screenpipe’s built-in chat
best setup: add screenpipe MCP to your main AI tool → setup guide.

​
recover from AI context loss

when an AI chat compacts or a coding agent forgets the last hour, screenpipe gives it somewhere real to look.
  • recent activity: “what did I do in the last 20 minutes?”
  • terminal recovery: “find the error I saw in Terminal before the chat reset”
  • meeting memory: “what did the customer ask for on the last call?”
  • browser trail: “what docs page was I reading before I switched apps?”
screenpipe does not recover hidden model context. it gives the AI a local, searchable memory of screen and audio history. best setup: connect the tool you already use through MCP, then ask it to cite screenpipe results before acting.

​
monitor your AI usage

how much time are you actually spending in ChatGPT vs. Claude? are you using AI effectively?
  • run AI Habits pipe: see which AI tools you use, for how long, and for what
  • track prompt patterns: the AI Prompt Journal shows your prompting habits over time
  • identify tool overlap: are you using 3 tools for the same thing?
best setup: run AI Habits pipe weekly.

​
manage relationships

remember everyone you meet, what you discussed, and when to follow up.
  • install Personal CRM pipe (8 installs): automatically builds relationship context from your screen and audio data
  • install Notion CRM Sync pipe (16 installs): auto-detects business calls and syncs contacts, deal stage, and action items to your Notion CRM
  • install Brand Listening pipe (4 installs): monitors topics around your brand based on your screen activity
best setup: install Notion CRM Sync if you use Notion, or Personal CRM for standalone relationship tracking.

​
monitor a specific app or window

some users want screenpipe to watch a narrow surface: a dashboard, trading terminal, ticket queue, internal tool, or customer app.
  • use included windows so only the target app is captured
  • start with content_type=all, then narrow to accessibility or ocr if needed
  • add a pipe that checks every few minutes and only alerts on a precise condition
  • test the notification path separately before trusting the automation
example: 
Every 5 minutes, search the last 10 minutes of screenpipe data for the window named "Operations Dashboard".
If a red error banner or failed status appears, send a desktop notification and write a short incident note.
If no matching data appears, log "no matching window data" instead of guessing.
best setup: recording filters + pipe debugging.

​
automate anything

if you can describe it, a pipe can do it. examples of pipes people have built and published:
  • Focus Assistant (38 installs) — detects when you’re distracted and sends a notification
  • Notion CRM Sync (16 installs) — auto-syncs business calls to your Notion CRM
  • Research Rabbit (10 installs) — deep-dives into topics you’re browsing, finds non-obvious insights
  • WisprFlow Sync (9 installs) — syncs voice recordings into screenpipe
or build your own — ask your AI coding tool: “create a screenpipe pipe that [what you want]” — full guide →. browse all pipes in the store →

​
for teams

share pipe configurations, enforce privacy filters, and standardize workflows across your team.
  • share pipes: push pipe configs to your whole team with end-to-end encryption
  • enforce filters: push window/URL ignore lists so the team has consistent privacy rules
  • team standups: everyone runs the same standup pipe, formatted the same way
best setup: teams guide →

​
get started

the fastest path: 5-minute quickstart → not sure where to start? enable Day Recap — it shows you what screenpipe captured and gives you ideas for what else you can do. need help? join our discord — 10k+ members.