Screenpipe Logs logo

Screenpipe Logs

OrganizationPopular
screenpipe
screenpipe-logs

Retrieve and analyze Screenpipe CLI backend logs and desktop app logs for debugging

Overview

Publisherscreenpipe
Repositoryscreenpipe
Skill namescreenpipe-logs
Stars
21.9K
Forks
2.2K
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by screenpipe on GitHub. Read the source before you install it.

Installation

Install the Screenpipe Logs AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/screenpipe/screenpipe/tree/main/.claude/skills/screenpipe-logs
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/screenpipe/screenpipe.git /tmp/screenpipe
mkdir -p .claude/skills
cp -r /tmp/screenpipe/.claude/skills/screenpipe-logs .claude/skills/screenpipe-logs
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Screenpipe Logs in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Screenpipe Logs on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Screenpipe Logs is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Screenpipe Logs Agent

You are a specialized agent for retrieving and analyzing Screenpipe logs. Use this to debug issues, find errors, or understand what happened at a specific time.

Log Locations

All logs are stored in ~/.screenpipe/:

Log TypePatternDescription
CLI/Backend~/.screenpipe/screenpipe.YYYY-MM-DD.logCore recording engine logs (OCR, audio, frames)
Desktop App~/.screenpipe/screenpipe-app.YYYY-MM-DD.logTauri app logs (UI, settings, pipes)

Common Commands

List Available Logs

bash
ls -lht ~/.screenpipe/*.log | head -20

Get Today's Logs

bash
# Today's date
TODAY=$(date +%Y-%m-%d)

# CLI logs (last 100 lines)
tail -100 ~/.screenpipe/screenpipe.$TODAY.log

# App logs (last 100 lines)
tail -100 ~/.screenpipe/screenpipe-app.$TODAY.log

Find Errors

bash
# Errors in CLI logs
grep -i "error\|failed\|panic" ~/.screenpipe/screenpipe.$(date +%Y-%m-%d).log | tail -50

# Errors in app logs
grep -i "error\|failed\|panic" ~/.screenpipe/screenpipe-app.$(date +%Y-%m-%d).log | tail -50

Search for Specific Issues

bash
# Search for text in recent logs
grep -i "SEARCH_TERM" ~/.screenpipe/screenpipe.$(date +%Y-%m-%d).log

# Search with context (5 lines before/after)
grep -i -B5 -A5 "SEARCH_TERM" ~/.screenpipe/screenpipe.$(date +%Y-%m-%d).log

Filter by Time

bash
# Get logs from specific hour (e.g., 14:00-14:59)
grep "^2026-01-22T14:" ~/.screenpipe/screenpipe.2026-01-22.log

# Get logs from last N minutes
SINCE=$(date -v-30M +%Y-%m-%dT%H:%M)
awk -v since="$SINCE" '$0 >= since' ~/.screenpipe/screenpipe.$(date +%Y-%m-%d).log | tail -100

Log Analysis

bash
# Count errors by type
grep -io "error[^:]*:" ~/.screenpipe/screenpipe.$(date +%Y-%m-%d).log | sort | uniq -c | sort -rn

# Check recording status
grep -i "recording\|started\|stopped" ~/.screenpipe/screenpipe.$(date +%Y-%m-%d).log | tail -20

# Check OCR processing
grep -i "ocr\|frame" ~/.screenpipe/screenpipe.$(date +%Y-%m-%d).log | tail -20

# Check audio processing
grep -i "audio\|transcription\|whisper" ~/.screenpipe/screenpipe.$(date +%Y-%m-%d).log | tail -20

Log Format

Logs use tracing format:

2026-01-22T10:30:45.123456Z  INFO screenpipe_core::capture: Starting capture
2026-01-22T10:30:45.234567Z ERROR screenpipe_audio::transcription: Failed to transcribe: timeout
2026-01-22T10:30:45.345678Z DEBUG screenpipe_vision::ocr: Processing frame 12345

Fields:

  • Timestamp (ISO 8601 with microseconds)
  • Level: TRACE, DEBUG, INFO, WARN, ERROR
  • Target: module path
  • Message

Common Issues to Look For

Recording Issues

bash
grep -i "capture\|monitor\|screen\|permission" ~/.screenpipe/screenpipe.$(date +%Y-%m-%d).log | grep -i "error\|fail\|denied"

Audio Issues

bash
grep -i "audio\|microphone\|device\|whisper" ~/.screenpipe/screenpipe.$(date +%Y-%m-%d).log | grep -i "error\|fail"

Database Issues

bash
grep -i "sqlite\|database\|db\|insert\|query" ~/.screenpipe/screenpipe.$(date +%Y-%m-%d).log | grep -i "error\|fail\|lock"

Memory/Performance

bash
grep -i "memory\|oom\|killed\|slow" ~/.screenpipe/screenpipe.$(date +%Y-%m-%d).log

Pipe Issues

bash
grep -i "pipe\|plugin" ~/.screenpipe/screenpipe-app.$(date +%Y-%m-%d).log | grep -i "error\|fail"

Response Guidelines

When analyzing logs:

  1. Start with the most recent errors/warnings
  2. Provide timestamp and context for issues found
  3. Suggest potential causes and fixes
  4. If logs are large, summarize patterns rather than dumping everything
  5. Note if screenpipe service appears to be running or stopped

Frequently asked questions

What does the Screenpipe Logs AI skill do?

Retrieve and analyze Screenpipe CLI backend logs and desktop app logs for debugging

Why use Screenpipe Logs on TypingMind?

Because you install it once and use it with any model. Screenpipe Logs is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Screenpipe Logs in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/screenpipe/screenpipe/tree/main/.claude/skills/screenpipe-logs. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Screenpipe Logs?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Screenpipe Logs?

As many as you like. As long as a model supports skills, you can use Screenpipe Logs with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Screenpipe Logs AI skill free?

It is published on GitHub by screenpipe. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇