Skip to main content

IMOS: Memory OS for Solo Professionals

 ██╗███╗   ███╗ ██████╗ ███████╗
 ██║████╗ ████║██╔═══██╗██╔════╝
 ██║██╔████╔██║██║   ██║███████╗
 ██║██║╚██╔╝██║██║   ██║╚════██║
 ██║██║ ╚═╝ ██║╚██████╔╝███████║
 ╚═╝╚═╝     ╚═╝ ╚═════╝ ╚══════╝
   IMOS: Solo Pro Memory OS

IMOS is your thoughtful local memory assistant - a powerful CLI tool that helps solo professionals organize, search, and interact with their personal knowledge base through intelligent semantic search and AI-powered conversations.

Features

  • Smart Memory Search: Semantic search across your personal knowledge base
  • AI-Powered Chat: Interactive conversations with your memories using Groq LLM
  • Automatic File Import: Support for .txt, .pdf, and .docx files
  • Action Item Tracking: Automatically detects and tracks TODOs from your notes
  • Memory Linking: Automatically connects related memories for richer context
  • Beautiful CLI: Professional, colored terminal interface with clear branding
  • Fast & Efficient: Vectorized operations and model caching for lightning-fast responses

Quick Start

Installation

pip install imos

Setup

  1. Get your free API key from Groq Console

  2. Set your API key:

export GROQ_API_KEY="your-key-here"

Or create a .env file:

echo "GROQ_API_KEY=your-key-here" > .env

Basic Usage

# Start an interactive chat with your memories
imos chat

# Ask a quick question
imos ask "What are my project goals?"

# Import a file
imos addfile notes.txt

# Import an entire folder
imos import-folder ~/Documents/Notes

# View action items
imos actions

# List all memories
imos list

Usage Examples

Interactive Chat Mode

$ imos chat
 ██╗███╗   ███╗ ██████╗ ███████╗
 ██║████╗ ████║██╔═══██╗██╔════╝
 ██║██╔████╔██║██║   ██║███████╗
 ██║██║╚██╔╝██║██║   ██║╚════██║
 ██║██║ ╚═╝ ██║╚██████╔╝███████║
 ╚═╝╚═╝     ╚═╝ ╚═════╝ ╚══════╝
   IMOS: Solo Pro Memory OS

IMOS Chat Mode Active
Type your question; type 'exit' to leave.

imos> What are my main project goals for this quarter?

You: What are my main project goals for this quarter?

IMOS> Based on your notes, your main project goals for this quarter include...

Primary sources:
  • /Users/you/Documents/Q4-Goals.txt
  • /Users/you/Notes/project-planning.md

Quick Questions

$ imos ask "What did I learn about Python optimization?"
IMOS Memory Search
Loading embedding model (one-time setup)...

IMOS> From your notes, you learned several key Python optimization techniques...

Primary sources:
  • /Users/you/Notes/python-performance.md
  • /Users/you/Documents/coding-tips.txt

File Import

$ imos import-folder ~/Documents/ProjectNotes
IMOS: Importing files from '/Users/you/Documents/ProjectNotes'...
  ✓ Imported: /Users/you/Documents/ProjectNotes/ideas.txt
  ✓ Imported: /Users/you/Documents/ProjectNotes/research.pdf
  ✓ Imported: /Users/you/Documents/ProjectNotes/meeting-notes.docx

IMOS: Import complete! 3 files imported, 0 failed

Action Tracking

$ imos actions
IMOS: Open Action Items
==================================================
[1] Review quarterly performance metrics
    Source: /Users/you/Notes/q4-review.txt | Added: 2024-11-09

[2] Follow up with client about project timeline
    Source: manual | Added: 2024-11-08

$ imos done 1
IMOS: Action 1 marked as done!

Commands Reference

Command Description
imos chat Start interactive chat mode
imos ask "question" Ask a quick question
imos add "text" Add a memory manually
imos addfile path/to/file Import a single file
imos import-folder path/ Import all supported files from a directory
imos actions List all open action items
imos done <id> Mark an action as completed
imos list List all stored memories
imos rebuild-links Rebuild memory connections

Configuration

Environment Variables

  • GROQ_API_KEY: Your Groq API key (required for chat features)

File Support

IMOS automatically extracts text from:

  • .txt files (plain text)
  • .pdf files (via PyMuPDF)
  • .docx files (Microsoft Word documents)

Data Storage

  • Memories are stored in a local SQLite database (memory.db)
  • Embeddings use the all-MiniLM-L6-v2 model for fast, efficient semantic search
  • No data is sent to external services except for LLM chat queries

Performance Features

  • Model Caching: Embedding model loads once and stays in memory
  • Vectorized Search: NumPy-optimized similarity calculations
  • Smart Context Management: Automatic conversation history trimming
  • Deduplication: Prevents storing duplicate content

Privacy & Security

  • All your memories stay local in SQLite database
  • Only chat queries are sent to Groq's API for processing
  • No tracking or analytics
  • Open source and transparent

Troubleshooting

Missing API Key

IMOS Setup Required!
To use chat features, please set your GROQ API key:
  export GROQ_API_KEY='your-key-here'
  or add it to your .env file

Get your free API key at: https://console.groq.com/keys

Installation Issues

# Upgrade pip first
pip install --upgrade pip

# Install with verbose output for debugging
pip install -v imos

File Import Errors

  • Ensure files are not corrupted
  • Check file permissions
  • Verify file format is supported (.txt, .pdf, .docx)

Development & Contributing

IMOS is open source! Visit our GitHub repository to:

  • Report issues
  • Submit feature requests
  • Contribute code
  • View the source

Support

License

IMOS is released under the MIT License. See LICENSE for details.


IMOS: Your memories, organized intelligently.

Metadata

Release files for imos 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for imos 0.1.0
File Size Uploaded Provenance Actions
imos-0.1.0.tar.gz 16.0 kB Without provenance Details for imos-0.1.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for imos 0.1.0
File Interpreter ABI Platform Actions
imos-0.1.0-py3-none-any.whl Python 3 none any Details for imos-0.1.0-py3-none-any.whl

Total release size: 30.6 kB

Release files / imos-0.1.0.tar.gz

Download URL imos-0.1.0.tar.gz
Size 16.0 kB
Tags Source
SHA-256 checksum
How to use checksums
e074125807613f2a191eafd3a2357a0b774b380112ac0167f1cdd0a37ffdcc60
BLAKE2b-256 checksum
How to use checksums
1edb07693014fde4a52db8f915a4f36dc468d8a3c45404f32e8201bd938382d0
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.4

Release files / imos-0.1.0-py3-none-any.whl

Download URL imos-0.1.0-py3-none-any.whl
Size 14.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
24006a9def9fc5918d12bd0d5fc9521785194674ae6afa6b64115bfda485aeab
BLAKE2b-256 checksum
How to use checksums
5b7154ca31176cf380c60d284b725023658afc4fec706ddb17368d78e92f5f0b
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.4

Security for imos 0.1.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page