npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@screenpipe/sync

v0.5.0

Published

Sync Screenpipe activity to structured daily summaries. Uses Claude Code CLI for AI extraction.

Downloads

22

Readme

screenpipe-sync

Sync your Screenpipe data to remote AI agents.

One-liner to permanently sync your screen memory to a remote server (e.g., Clawdbot, any SSH server). Your AI agent can then query your full history via SQLite.

Also extracts structured daily summaries: todos, goals, decisions, and AI insights.

Quick Start

# One-liner - AI summary to stdout
bunx @screenpipe/sync

# Save daily summaries locally
bunx @screenpipe/sync --output ~/Documents/brain/context --git

# Sync raw SQLite database to remote (full history!)
bunx @screenpipe/sync --db --remote user@host:~/.screenpipe/

# Full sync: DB + daily summary
bunx @screenpipe/sync --db -r clawdbot:~/.screenpipe && bunx @screenpipe/sync -o ~/context -g

What It Extracts

| Category | Description | |----------|-------------| | Todos | Action items visible on screen or mentioned | | Goals | Objectives, intentions, targets mentioned | | Decisions | Choices made or discussed | | Activities | Key tasks worked on, by app | | Meetings | Calls, conversations, collaborations | | Blockers | Problems, frustrations, obstacles | | Insights | AI observations about work patterns |

Example Output

# Daily Context - 2026-01-29

> Analyzed 480 minutes of screen activity

## 📱 Apps Used
- **VS Code**: ~180 min
- **Chrome**: ~120 min
- **Slack**: ~60 min

## ✅ Todos Extracted
- Fix authentication bug in login.ts
- Review PR #234 for payment integration
- Send weekly update to investors

## 🎯 Goals Mentioned
- Ship v2.9 by Friday
- Reach 50% activation rate

## 💡 AI Insights
- Heavy context switching between Slack and VS Code (17 switches/hour)
- Deep focus block from 2-4pm on auth refactor
- Late session (after 10pm) - consider sleep impact

Options

| Flag | Description | Default | |------|-------------|---------| | -o, --output <dir> | Save to directory | stdout | | -h, --hours <n> | Hours to analyze | 12 | | -g, --git | Auto commit & push | false | | -r, --remote <host> | Sync via SSH | - | | --json | JSON output | markdown | | -v, --verbose | Debug output | false |

Environment Variables

# AI Provider (uses first available)
export ANTHROPIC_API_KEY="sk-..."     # Claude (recommended)
export OPENAI_API_KEY="sk-..."        # OpenAI fallback
export OLLAMA_URL="http://localhost:11434"  # Local Ollama
export OLLAMA_MODEL="llama3.2"        # Ollama model

# Screenpipe
export SCREENPIPE_URL="http://localhost:3030"  # Default

AI Priority: Claude → OpenAI → Ollama → No AI (basic summary)

Use Cases

Daily Journaling

# Run at end of day
bunx @screenpipe/sync --output ~/journal --hours 16

Sync to Remote AI Assistant

# Sync context to Clawdbot/Moltbot instance
bunx @screenpipe/sync --output ~/brain/context --git
# Remote pulls via cron

Weekly Review Prep

# Get full week
bunx @screenpipe/sync --hours 168 --json > week.json

Automated Daily Sync (cron)

# Add to crontab
0 22 * * * ANTHROPIC_API_KEY=sk-... bunx @screenpipe/sync -o ~/context -g

How It Works

Summary Mode (default)

  1. Query - Fetches OCR data from local Screenpipe API
  2. Dedupe - Removes duplicate/similar screen captures
  3. Extract - Claude analyzes content for structured data
  4. Format - Outputs markdown or JSON
  5. Sync - Optionally git pushes or SCPs to remote

DB Sync Mode (--db)

  1. Copy - Copies ~/.screenpipe/db.sqlite (your full history)
  2. Sync - Uses rsync/scp to transfer to remote
  3. Query - Remote can query SQLite directly
# On remote, query your full history:
sqlite3 ~/.screenpipe/db.sqlite "SELECT text FROM ocr_text WHERE text LIKE '%meeting%' LIMIT 10;"

Requirements

  • Screenpipe running locally
  • Bun runtime
  • Anthropic API key for AI extraction (optional but recommended)

Privacy

All processing happens locally. Screen data never leaves your machine unless you explicitly sync to a remote.

License

MIT - Part of the Screenpipe project.