Jotit – command-line notes with AI search and summaries

15 hours ago 1

A command-line tool to quickly take notes, then use AI for search, and summaries.

One of the problems with taking notes is always having to think about the file you're creating, where you're going to put it, what to name it, folder structures, etc. All these things get in the way of taking quick notes.

So I thought can AI help eliminate this friction?

Quick Note Capture: Add notes instantly from the command line
Semantic Search: Find notes using natural language, not just keywords
AI Summarization: Get intelligent summaries of your notes over time
Background Processing: Embeddings and AI features used when needed
SQLite-based: Reliable local storage with vector search capabilities

Not on Pypi yet, so: python -m pip install git+https://github.com/mkaz/jotit

Requires Python 3.10 or higher

git clone https://github.com/mkaz/jotit.git cd jotit uv pip install .

Set up your API key (optional)

For AI-powered search and summaries, set your Anthropic API key:

export ANTHROPIC_API_KEY="your-api-key-here"

# Simple note jotit "Had a great idea about improving user onboarding" # With a tag jotit "Met with the design team about the new homepage" --tag "meeting" # From stdin git log --since 2025-10-31 | jotit

# List notes by recency jotit list # List notes from a specific date jotit list --date 2024-01-15 jotit list --after 2024-01-01 jotit list --before 2024-12-31 # List notes by tag jotit list --tag "work" # Show all available tags jotit tags

Requires AI API key set.

# Semantic search - finds related concepts even if exact words don't match jotit search "design discussions" # Semantic search scoped to a tag jotit search "roadmap updates" --tag "product"

Requires AI API key set.

# Get a summary of recent notes (defaults to last 5 days) jotit summary jotit summary [week|month] jotit summary --days 30 # Last 30 days jotit summary --after 2024-01-01 # Since specific date jotit summary --before 2024-02-01 # Up to but not including Feb 1

To enable fast note creation, the embeddings are moved to background jobs which can be called manually using worker or will be called when a task requires it, such as search or summary.

jotit worker # Process all pending jobs jotit worker --batch-size 10 # Limit number of jobs processed

jotit edit 123 # Edit note 123 jotit delete 456 # Delete note 456 jotit import /path/to/notes/ # Bulk import notes from directory

# Show database statistics jotit stats

Jotit can be configured via environment variables or a TOML configuration file located at ~/.config/jotit/jotit.toml. See jotit-sample.toml for a complete example with all available options.

ANTHROPIC_API_KEY - Required for AI-powered summaries
JOTIT_DB - Database file location (default: ./jotit.db)

Create ~/.config/jotit/jotit.toml to customize default behavior:

[database] # Default database path - uses ~/.config/jotit/jotit.db if not overridden by JOTIT_DB env var path = "~/.config/jotit/jotit.db" [ai] # Default AI model for summarization and question answering model = "claude-sonnet-4-5-20250929" [embedding] # Embedding model for semantic search model = "all-MiniLM-L6-v2" [search] # Default similarity threshold for search results (0.0-1.0) # Higher values return only more relevant results, lower values are more inclusive # Set to 0.0 to disable threshold filtering threshold = 0.40 # Enable hybrid search by default # Hybrid search boosts results that contain exact keyword matches from your query # This improves precision when searching for specific terms or phrases hybrid = true

Setup Development Environment

git clone https://github.com/mkaz/jotit.git cd jotit # Create virtual environment python -m venv .venv source .venv/bin/activate # On Windows: .venv\Scripts\activate # Install in development mode just install-dev

Jotit uses just for task automation:

just install # Install package just install-dev # Install in editable mode for development just test # Run test suite just lint # Check code with ruff linter just lint-fix # Auto-fix linting issues just format # Format code with ruff just type-check # Run type checking with mypy just check # Run all quality checks just clean # Remove build artifacts

# Run all tests just test # Run specific test file pytest tests/test_db.py # Run with coverage pytest --cov=jotit --cov-report=html

MIT License - see LICENSE file for details.

Created by Marcus Kazmierczak

Jotit - jot it down, find it later

Read Entire Article