Your personal AI that builds memory through screen observation and natural conversation
| 🌐 Website | 📚 Documentation | 📄 Paper |
- 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
End-Users: For end-users who want to build your own memory using MIRIX, please checkout the quick installation guide here.
Developers: For users who want to apply our memory system as the backend, please check out our Backend Usage. Basically, you just need to run:
git clone git@github.com:Mirix-AI/MIRIX.git
cd MIRIX
# Create and activate virtual environment
python -m venv mirix_env
source mirix_env/bin/activate # On Windows: mirix_env\Scripts\activate
pip install -r requirements.txt
Then you can run the following python code:
from mirix.agent import AgentWrapper
# Initialize agent with configuration
agent = AgentWrapper("./configs/mirix.yaml")
# Send basic text information
agent.send_message(
message="The moon now has a president.",
memorizing=True,
force_absorb_content=True
)For more details, please refer to Backend Usage.
Mirix is released under the Apache License 2.0. See the LICENSE file for more details.
For questions, suggestions, or issues, please open an issue on the GitHub repository or contact us at yuw164@ucsd.edu
Connect with other Mirix users, share your thoughts, and get support:
 Discord Community |
 WeChat Group |
We would like to thank Letta for open-sourcing their framework, which served as the foundation for the memory system in this project.