mcp-server

screenpipe: Capture Your Day‑to‑Day AI Memory with 22k+ Stars

Turn every screen, voice, and sound into searchable context for your AI apps. Ideal for founders building privacy‑first, multimodal products.

From the repo · “YC (S26) | Open Computer History | Record your screen continuously locally and provide context to your agents (Claude, Codex, Openclaw, Hermes, Runner...)”

intermediate⏱ 30 minutes💵 Free (self-hosted)
22,027 stars+83★ this week2,251 forksRustGuide quality 8/10 · reviewed Oct 5Updated 10/22/2026100% free · open source
What it is

With screenpipe, you record your daily interactions to teach AI about your experiences.

Real use case example

"A founder, Sarah, wants to build an application that automatically assigns tasks to team members based on their work style. She uses screenpipe to record her daily interactions and teaches the AI to identify patterns. After a week of recordings, she fine-tunes the model and integrates it with Trello to automate task assignment."

When to use it
  • •When you want to review complex meetings or coding sessions you might have forgotten details about
  • •For founders tracking their productivity and workflow patterns
  • •To create a personal knowledge base of your digital interactions
Ready-to-paste prompt
screenpipe search 'project funding discussion from last week'
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/screenpipe && curl -fsSL https://workflowstacks.com/api/skills/screenpipe/claude-skill -o ~/.claude/skills/screenpipe/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How screenpipe: Capture Your Day‑to‑Day AI Memory with 22k+ Stars works
Codeflow
Free to inspect

Screenpipe: Capture Your Day‑to‑Day AI Memory with 22k+ Stars is a very large Rust project (~831k lines across 2339 code files, plus 631 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Other license, has a test suite.

Size
Very large codebase
~831k lines · 2339 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Rust
No API keys detected
Rust 53%TypeScript 42%Swift 2%JavaScript 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    Cargo.toml
    Dependencies and the commands it exposes
What's in each folder
apps/Sub-packages / plugins1893 files
packages/Sub-packages / plugins345 files
docs/Documentation377 files
crates/Folder1164 files
infra/Deployment / infrastructure31 files
scripts/Helper scripts28 files
evals/Evaluations & benchmarks9 files
.github/CI / automation (GitHub Actions)154 files
READMEHas testsDocumentedCI checksOther licenseUpdated this month
Quick Actions
Details
Creator
screenpipe
Language
Rust
Category
mcp-server
Published
6/19/2024

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/screenpipe.svg)](https://workflowstacks.com/skills/screenpipe?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.