Screenpipe logoscreenpipe
screenpipe teams

Your team loses hours every day to invisible busywork.

Process discovery, task mining, and AI automation — on every workstation. Screenpipe captures every workflow across your org and deploys agents that eliminate manual busywork. 100% local. Zero data leaves any device.

Worktrace AI
Worktrace AI — built on screenpipe. founded by the creator of ChatGPT.
comparison

The only tool that captures everything and leaks nothing.

Screen, audio, keyboard, clipboard — across Mac, Windows, and Linux. 100% local. Open source. No other tool comes close.

featurescreenpipeothers
100% local data
Open source
Screen capture
Some
Audio capture
Meetings only
Keyboard & clipboard
Rare
Cross-platformMac, Win, Linux1–2 platforms
Mobile (iOS, Android)Coming soonRare
On-prem deployment
Rare
Local LLM compatibleOllama, Apple AI, Windows AI
AI agent permissionsPer-pipe YAML policies
MDM deploymentIntune, SCCM, RobopackSome
Employee privacy controlsPause, override, view own dataLimited or none
Developer API
Rare
Employee sees own data
Rare
how it works

Three steps. Zero data sharing.

step 1

Admin creates config

Define what to capture, which apps to monitor, schedules, and URL filters.

screen capture
audio capture
app filters
schedule
step 2

Push to team

Config syncs to every team member's device instantly.

A
B
C
D
synced to 4 devices
step 3

Runs locally

Each device runs screenpipe independently. Data never leaves the machine.

config editor

Define what your team captures

Centrally manage capture settings, pushed to every device

Team config

engineering-team.json

pushed to 0 devices
app filters
🌐Chrome
💬Slack
📝VSCode
📹Zoom
url rules
block: *bank*.com
block: *health*.gov
allow: github.com/*
allow: linear.app/*
schedule
00:0009:0018:0023:59
shared pipes

AI workflows that run on every machine

Push pipes to the team. Each device processes locally, outputs flow to shared tools.

team
A
B
C
D
pipes
📋
🎙️
⏱️
outputs
💬
📐
📝
auto-standup

daily summary → Slack

meeting-to-linear

action items → tickets

time-tracker

app usage → Notion log

slack

#standup — auto-generated

Alice: worked on auth refactor, reviewed 3 PRs. Bob: fixed deployment pipeline, pair programmed with Carol.

linear

PIPE-142: Update onboarding flow

From meeting @ 2:30pm — Carol mentioned the signup form needs validation. Assigned: Dave. Priority: High.

notion

Time log — Feb 18

VSCode: 4.2h | Chrome: 2.1h | Slack: 1.3h | Zoom: 0.8h — Total productive: 7.1h

privacy boundary

Configs flow down. Data stays put.

Admins control what gets captured. They never see the captures themselves.

read security whitepaper

What admin controls

capture policies

capture schedule9am — 6pm
app filterschrome, slack, vscode
url rulesblock *bank*.com

What stays private

on each device

screenshots
audio
text content
browsing history
override rules
adminsets: ignore banking apps
employeeadds: also ignore personal email
employeetries to remove banking filter
storage & architecture

Your data. Your hardware. Period.

Each device stores its own data in a local SQLite database. No shared database, no cloud requirement, no single point of failure.

where data lives

each device, independently

mac-01
2.1 GB
mac-02
3.4 GB
win-03
1.8 GB
per device
db~/.screenpipe/db.sqlite
media~/.screenpipe/data/
growth~5–10 GB / month
retentionconfigurable auto-delete

optional backup

your infrastructure, your rules

SFTP to NASbuilt-in, scheduled sync to your server
encrypted cloudzero-knowledge, opt-in per device
no shared DBeach device has its own SQLite — no conflicts
device
your NAS
(read-only backup)
employee experience

Your team won't even notice it.

Runs silently in the background. No popups, no slowdowns. Employees keep full control over their privacy.

what employees see

a tray icon. that's it.

<2%cpu
0alerts
2 minsetup

employee controls

privacy is a right, not a feature

add stricter filters

block personal apps beyond admin rules

pause anytime

take a break, no questions asked

see your own data

search and review everything captured

remove admin filters

company policies stay enforced

ai data permissions

Deterministic control over what AI can access

Define per-pipe data permissions in YAML frontmatter. Enforced at the OS level — not by prompting the AI to behave.

pipe.md frontmatter
---
permissions:
allow:
- Api(GET /search)
- Api(GET /activity-summary)
- App(Slack, VS Code)
- Content(ocr, audio)
deny:
- App(1Password, Signal)
- Window(*incognito*, *bank*)
- Content(input)
time: "09:00-17:00"
days: "Mon-Fri"
---
three enforcement layers
layer 1 — skill gating

Denied endpoints are never taught to the AI. Deny rules are evaluated first — they always win over allow rules.

layer 2 — agent interception

Every API call is intercepted at the OS level before execution. Forbidden requests are blocked in-process.

layer 3 — server middleware

Per-pipe tokens validated server-side. Even if the agent is compromised, the API rejects unauthorized requests.

App & window filtering

Allow or deny specific apps and window title patterns. Deny always wins.

Content type control

Restrict to "ocr", "audio", "input", or "accessibility" — block what the AI should never touch.

Time & day restrictions

Limit data access to business hours (e.g. 09:00-18:00, Mon-Fri). Supports midnight wrap.

Endpoint gating

Control API access per pipe — allow GET /search but deny POST /meetings/stop. Glob patterns supported.

Presets or custom rules

Use presets like "reader" or "admin" for quick setup, or define granular allow/deny rules per pipe.

Per-pipe tokens

Each pipe run gets a unique cryptographic token. Server validates every request.

use cases

From process discovery to agentic automation

Capture every workflow. Find hidden inefficiencies. Deploy AI agents that automate the busywork — CRM updates, meeting notes, reporting. All on-device.

Process Discovery & Task Mining

See hidden workflows

  • Capture every screen, app switch, and workflow across your org — automatically
  • Map how work actually happens — not how people say it does
  • Identify bottlenecks, redundant steps, and automation opportunities

Agentic Automation

Deploy AI agents at scale

  • Meeting ends → CRM updated with notes, attendees, and next steps
  • Standups, reports, and handoffs written from real activity — not memory
  • Custom AI workflows deployed to every device via admin config

Time & Activity Intelligence

Eliminate manual tracking

  • Billable hours logged without anyone lifting a finger
  • App and tool usage patterns across your entire team
  • Weekly reports generated from real data, not guesswork

Business Process Optimization

Continuous improvement

  • Before/after workflow comparison — measure the impact of changes
  • Connect to Slack, Notion, CRM — automate data flow between tools
  • AI agents that act on what your team actually does, not what they report

Computer Use & AI Training Data

Turn workflows into AI agents

  • Record how your best employees work — every click, keystroke, and decision
  • Export structured workflow datasets to train computer-use AI agents
  • Build internal automation from real human behavior, not synthetic demos

Compliance & Security

Audit-ready from day one

  • Data never leaves the device — no cloud, no breach surface
  • SOC 2 Type II certified with per-employee privacy controls
  • Open source — audit every line of code
read security whitepaper
pricing

Cheaper than the problem it solves

One workflow audit costs more than a year of Screenpipe for your entire team. And Screenpipe never goes stale.

Trusted byWeekly call with the team to review your workflows17,000+ developers trust screenpipeOpen source — audit every line of code
most teams start here

Team

Workflow intelligence and AI automation for growing teams.

$
per seat · per month
  • Full workflow capture across every device
  • AI-powered time tracking & standup generation
  • Admin dashboard with team-wide insights
  • Shared AI workflows deployed to all devices
  • Centralized config management
  • Employee privacy controls built in
  • Weekly strategy call with our team
  • Priority support + onboarding call
Book a demo

or leave your email — we'll reach out

Enterprise

For organizations that need compliance, security, and scale.

Customcustom pricing
  • Everything in Team
  • SSO / SAML authentication
  • Complete audit trail & compliance logs
  • Three-layer AI permission enforcement
  • Dedicated account manager
  • Weekly workflow review with your account team
  • Managed rollout & MDM deployment
  • SLA with 99.9% uptime guarantee
  • SOC 2 Type II certified
  • Custom integrations & storage policies
  • Volume pricing for 50+ seats
Talk to sales
the math

A 50-person team wastes ~$1.2M/year on invisible inefficiency

45 min
avg. daily time lost to context switching per employee*
$50K+
cost of a one-time workflow audit (stale in weeks)
17K+
developers trust screenpipe (open source on GitHub)

Screenpipe for 50 seats costs less per month than one day of a management consultant.

* Based on research from the American Psychological Association and University of California, Irvine on task-switching costs