MIRIX is an AI agent state orchestrator and long-term memory system designed to provide persistent context for large language models. It functions as a multi-modal AI memory pipeline that processes text, voice, and screen captures into structured knowledge stores, including a dedicated screen activity knowledge base.
The project distinguishes itself by integrating a multi-modal observation pipeline that monitors desktop activity in real-time to build a searchable history of user actions. It utilizes a multi-tiered memory hierarchy—separating episodic, semantic, procedural, and core stores—and coordinates shared memory pipelines across multiple agents to maintain a unified knowledge base.
The system includes broad capabilities for memory management and retrieval, utilizing hybrid vector-keyword search, temporal filtering, and automated memory lifecycle coordination. It also incorporates security features such as local data encryption, risk-based data categorization, and sensitivity-based result filtering to ensure user memory isolation.
The project is implemented in Python and supports integration with OpenAI-compatible API endpoints and various vector database backends.