Thanks to visit codestin.com
Credit goes to Github.com

Skip to content
forked from Mirix-AI/MIRIX

Mirix is a multi-agent personal assistant designed to track on-screen activities and answer user questions intelligently. By capturing real-time visual data and consolidating it into structured memories, Mirix transforms raw inputs into a rich knowledge base that adapts to your digital experiences.

License

Notifications You must be signed in to change notification settings

damrongsak/MIRIX

 
 

Repository files navigation

Mirix Logo

MIRIX - Multi-Agent Personal Assistant with an Advanced Memory System

Your personal AI that builds memory through screen observation and natural conversation

| 🌐 Website | 📚 Documentation | 📄 Paper |


Key Features 🔥

  • Multi-Agent Memory System: Six specialized memory components (Core, Episodic, Semantic, Procedural, Resource, Knowledge Vault) managed by dedicated agents
  • Screen Activity Tracking: Continuous visual data capture and intelligent consolidation into structured memories
  • Privacy-First Design: All long-term data stored locally with user-controlled privacy settings
  • Advanced Search: PostgreSQL-native BM25 full-text search with vector similarity support
  • Multi-Modal Input: Text, images, voice, and screen captures processed seamlessly

License

Mirix is released under the Apache License 2.0. See the LICENSE file for more details.

Contact

For questions, suggestions, or issues, please open an issue on the GitHub repository or contact us at [email protected]

Acknowledgement

We would like to thank Letta for open-sourcing their framework, which served as the foundation for the memory system in this project.

About

Mirix is a multi-agent personal assistant designed to track on-screen activities and answer user questions intelligently. By capturing real-time visual data and consolidating it into structured memories, Mirix transforms raw inputs into a rich knowledge base that adapts to your digital experiences.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 83.3%
  • JavaScript 12.6%
  • CSS 4.0%
  • Other 0.1%