# mirix-ai/mirix

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/mirix-ai-mirix).**

3,535 stars · 287 forks · Python · apache-2.0

## Links

- GitHub: https://github.com/Mirix-AI/MIRIX
- Homepage: https://mirix.io/
- awesome-repositories: https://awesome-repositories.com/repository/mirix-ai-mirix.md

## Topics

`llm-agents` `llm-memory` `memory-agents` `personal-assistant`

## Description

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.

## Tags

### Artificial Intelligence & ML

- [Stateful Agent Orchestrators](https://awesome-repositories.com/f/artificial-intelligence-ml/stateful-agent-orchestrators.md) — Functions as a stateful orchestrator for managing agent personas, system prompts, and persistence in multi-step processes.
- [Long-term Memory Stores](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/memory-management-systems/long-term-memory-stores.md) — Implements persistent storage mechanisms that allow AI agents to retain context and recall facts across multiple sessions.
- [Agent Memory Categorization](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-memory-categorization.md) — Uses specialized agents to categorize user activities into structured episodic, semantic, and procedural memory types. ([source](https://docs.mirix.io/legacy/getting-started/installation/))
- [Screen Activity Classifiers](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-powered-observability-analysis/screen-activity-classifiers.md) — Processes periodic screenshots of desktop activity to classify events and build a chronological memory of user actions. ([source](https://docs.mirix.io/legacy/getting-started/installation/))
- [Context-Aware Conversation Managers](https://awesome-repositories.com/f/artificial-intelligence-ml/context-aware-retrieval/context-aware-conversation-managers.md) — Orchestrates multi-turn dialogues by combining language models with retrieved memory to provide contextually relevant assistance. ([source](https://docs.mirix.io/legacy/user-guide/desktop-app/))
- [Context Memory Management](https://awesome-repositories.com/f/artificial-intelligence-ml/context-memory-management.md) — Directs multi-modal inputs to specialized memory components to maintain a structured context for the AI.
- [Embedding Models](https://awesome-repositories.com/f/artificial-intelligence-ml/embedding-models.md) — Provides configurations for embedding models to support semantic search and long-term memory retrieval. ([source](https://docs.mirix.io/memory-write/configuration/))
- [Episodic Event Recording](https://awesome-repositories.com/f/artificial-intelligence-ml/episodic-event-recording.md) — Captures context-specific activities and behaviors to serve as a chronological summary of events. ([source](https://docs.mirix.io/architecture/memory-components/))
- [Persistent Context Management](https://awesome-repositories.com/f/artificial-intelligence-ml/persistent-context-management.md) — Maintains persistent agent context by storing key facts and decisions across multiple user sessions. ([source](https://docs.mirix.io/))
- [Procedural Knowledge Capture](https://awesome-repositories.com/f/artificial-intelligence-ml/step-by-step-task-plans/procedural-knowledge-capture.md) — Records step-by-step instructions and operational patterns required to accomplish recurring tasks. ([source](https://docs.mirix.io/architecture/memory-components/))
- [Visual Activity Knowledge Bases](https://awesome-repositories.com/f/artificial-intelligence-ml/visual-activity-knowledge-bases.md) — Monitors desktop activity and converts visual observations into a searchable long-term memory store.
- [Visual Context Monitors](https://awesome-repositories.com/f/artificial-intelligence-ml/visual-context-monitors.md) — Analyzes desktop activity in real-time to provide AI assistance based on current visual context. ([source](https://docs.mirix.io/legacy/user-guide/desktop-app/))
- [Multi-Agent Coordination Systems](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/orchestration-engines/ai-agent/multi-agent-coordination-systems.md) — Integrates a unified memory pipeline across multiple agents to enable state sharing and collaborative knowledge access.
- [Agent Persona Configurations](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-persona-configurations.md) — Defines assistant behaviors and system prompts while maintaining consistent user personas and identity facts.
- [Custom Tool Registrations](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-tool-integrations/custom-tool-registrations.md) — Implements mechanisms for registering and attaching custom user-defined functions as tools that agents can execute. ([source](https://docs.mirix.io/legacy/user-guide/custom-tools/))
- [OpenAI-Compatible APIs](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/model-integration-serving/model-integration-interfaces/ai-integration-apis/openai-compatible-apis.md) — Integrates with OpenAI-compatible API endpoints to leverage both fine-tuned and self-hosted models. ([source](https://docs.mirix.io/legacy/user-guide/custom-models/))
- [Persona Configurations](https://awesome-repositories.com/f/artificial-intelligence-ml/custom-ai-assistant-development/persona-configurations.md) — Provides configuration settings and prompt templates to define the personality and behavioral constraints of the AI agent. ([source](https://docs.mirix.io/legacy/user-guide/desktop-app/))
- [Editable User Persona Memory](https://awesome-repositories.com/f/artificial-intelligence-ml/memory-provenance-tracking/user-personalization-traces/editable-user-persona-memory.md) — Maintains structured and editable storage of user preferences and identity facts to personalize agent interactions. ([source](https://docs.mirix.io/architecture/multi-agent-system/))
- [Per-User Memory Isolation](https://awesome-repositories.com/f/artificial-intelligence-ml/memory-provenance-tracking/user-personalization-traces/editable-user-persona-memory/per-user-memory-isolation.md) — Queries memories across an organization while using strict isolation to ensure user-specific data remains private. ([source](https://docs.mirix.io/memory-search/search/))
- [Memory Decay Policies](https://awesome-repositories.com/f/artificial-intelligence-ml/memory-relevance-controls/memory-decay-policies.md) — Controls information longevity by marking memories as inactive or deleting them after a set duration. ([source](https://docs.mirix.io/memory-write/configuration/))
- [System Prompt Overrides](https://awesome-repositories.com/f/artificial-intelligence-ml/model-behavioral-analysis/system-prompt-overrides.md) — Allows overriding default agent behaviors by modifying or appending instructions via custom system prompts. ([source](https://docs.mirix.io/legacy/user-guide/custom-models/))
- [Model Selection Tools](https://awesome-repositories.com/f/artificial-intelligence-ml/model-selection-tools.md) — Offers utilities for selecting specific large language models based on performance and cost requirements for different tasks. ([source](https://docs.mirix.io/legacy/user-guide/desktop-app/))
- [Procedural Memory Retrievals](https://awesome-repositories.com/f/artificial-intelligence-ml/procedural-memory-retrievals.md) — Implements specialized querying of structured arrays of step-by-step instructions to recall specific workflows. ([source](https://docs.mirix.io/architecture/search-capabilities/))
- [Hybrid Search Methods](https://awesome-repositories.com/f/artificial-intelligence-ml/vector-similarity-search/hybrid-search-methods.md) — Combines full-text BM25 ranking with vector similarity search and relational filters for optimized memory recall. ([source](https://docs.mirix.io/architecture/search-capabilities/))

### Data & Databases

- [Observation Ingestion Pipelines](https://awesome-repositories.com/f/data-databases/multi-modal-search-engines/multi-modal-rag-pipelines/observation-ingestion-pipelines.md) — Ingests continuous screen captures and audio to transform real-time visual activity into structured long-term memories.
- [Multi-Tier Memory Systems](https://awesome-repositories.com/f/data-databases/tiered-caching-systems/multi-tier-memory-systems.md) — Implements a multi-tier memory system that separates data into core, episodic, semantic, and procedural stores. ([source](https://docs.mirix.io/getting-started/overview/))
- [Hybrid Vector and Full-Text Search](https://awesome-repositories.com/f/data-databases/hybrid-vector-and-full-text-search.md) — Combines vector similarity and full-text keyword matching to optimize the recall of long-term memories.
- [Conversation Memory Retrieval](https://awesome-repositories.com/f/data-databases/indexing-and-search/recall-optimization/conversation-memory-retrieval.md) — Fetches relevant stored memories based on current conversation state to provide historical context for AI interactions. ([source](https://docs.mirix.io/getting-started/quickstart/))
- [Knowledge Management](https://awesome-repositories.com/f/data-databases/knowledge-management.md) — Stores abstracted concepts and factual information in a dedicated knowledge management system independent of specific events. ([source](https://docs.mirix.io/architecture/memory-components/))
- [Local-First Storage](https://awesome-repositories.com/f/data-databases/local-first-storage.md) — Implements local-first storage strategies to ensure user data sovereignty and manages information via retention policies. ([source](https://docs.mirix.io/getting-started/overview/))
- [Multi-Modal Memory Stores](https://awesome-repositories.com/f/data-databases/multi-modal-data-management/multi-modal-preprocessing-pipelines/multi-modal-memory-stores.md) — Processes text, voice, and screen captures into a unified multi-modal memory store for richer AI context.
- [Multi-Modal RAG Pipelines](https://awesome-repositories.com/f/data-databases/multi-modal-search-engines/multi-modal-rag-pipelines.md) — Analyzes text, images, and voice simultaneously through a RAG pipeline to extract information from multi-modal inputs. ([source](https://docs.mirix.io/legacy/user-guide/backend-usage/))
- [Vector Memory Stores](https://awesome-repositories.com/f/data-databases/vector-memory-stores.md) — Manages AI memories using a hybrid of vector similarity and keyword indexing with customizable retention policies.
- [Knowledge Structuring](https://awesome-repositories.com/f/data-databases/content-extraction/knowledge-structuring.md) — Organizes core facts and procedures into structured components with configurable retention and decay policies. ([source](https://docs.mirix.io))
- [Risk-Based Classifications](https://awesome-repositories.com/f/data-databases/data-categorization/risk-based-classifications.md) — Categorizes sensitive information by risk level to prevent the accidental exposure of high-security data. ([source](https://docs.mirix.io/architecture/multi-agent-system/))
- [Chat Query Engines](https://awesome-repositories.com/f/data-databases/data-visualization-charts/natural-language-querying/natural-language-to-sql/chat-query-engines.md) — Implements a chat-based query engine to answer natural-language questions based on recorded historical information. ([source](https://docs.mirix.io/legacy/user-guide/backend-usage/))
- [Local Database Security](https://awesome-repositories.com/f/data-databases/local-database-security.md) — Ensures long-term memories are stored on local infrastructure using database-level security and encryption. ([source](https://docs.mirix.io))
- [Multi-Backend Storage Management](https://awesome-repositories.com/f/data-databases/multi-backend-storage-management.md) — Supports multiple storage backends, including scalable vector search and lightweight fallbacks, through a unified management layer. ([source](https://docs.mirix.io/legacy/getting-started/installation/))
- [Pluggable Database Backends](https://awesome-repositories.com/f/data-databases/persistent-storage-backends/pluggable-database-backends.md) — Decouples the memory pipeline from the storage layer, allowing interchangeable local or hosted database backends.
- [Cross-Category Memory Search](https://awesome-repositories.com/f/data-databases/search-indexing-technologies/search-indexing/search-and-indexing/cross-category-memory-search.md) — Retrieves relevant information using unified queries across different memory categories. ([source](https://docs.mirix.io/architecture/memory-components/))
- [Multi-Pass Query Strategies](https://awesome-repositories.com/f/data-databases/search-indexing/complex-search-querying/multi-pass-query-strategies.md) — Executes a sequence of search strategies, moving from high-precision matches to broader retrievals to optimize recall. ([source](https://docs.mirix.io/architecture/search-capabilities/))

### Business & Productivity Software

- [Desktop Activity Tracking](https://awesome-repositories.com/f/business-productivity-software/activity-trackers/desktop-activity-tracking.md) — Monitors desktop activity in real-time to build a structured, searchable history of user actions. ([source](https://docs.mirix.io/architecture/memory-components/))

### Development Tools & Productivity

- [Screen Capture Tools](https://awesome-repositories.com/f/development-tools-productivity/screen-capture-tools.md) — Captures continuous visual data from the screen to be consolidated into structured AI memories. ([source](https://cdn.jsdelivr.net/gh/mirix-ai/mirix@main/README.md))
- [Agent Session Recovery](https://awesome-repositories.com/f/development-tools-productivity/crash-recovery-systems/agent-session-recovery.md) — Saves and reloads agent memory states to preserve knowledge and context across different sessions. ([source](https://docs.mirix.io/legacy/user-guide/backend-usage/))
- [Sandboxed Execution Environments](https://awesome-repositories.com/f/development-tools-productivity/sandboxed-execution-environments.md) — Executes custom tool functions and API integrations within an isolated environment for safe agent extension.
- [Temporal Activity Filters](https://awesome-repositories.com/f/development-tools-productivity/temporal-activity-filters.md) — Provides capabilities to restrict memory retrieval results based on specific timestamp ranges or time offsets. ([source](https://docs.mirix.io/architecture/search-capabilities/))

### Networking & Communication

- [Procedural Memory Captures](https://awesome-repositories.com/f/networking-communication/remote-procedure-execution/standard-operating-procedures/procedural-memory-captures.md) — Records step-by-step workflows and recurring task patterns to create a searchable library of operational instructions.

### Operating Systems & Systems Programming

- [Memory Entry Lifecycles](https://awesome-repositories.com/f/operating-systems-systems-programming/kernel-core-internals/process-and-memory-management/memory-entry-lifecycles.md) — Automatically manages memory lifecycles by archiving old entries, merging duplicates, and expiring outdated credentials. ([source](https://docs.mirix.io/architecture/memory-components/))
- [Multi-Modal Memory Routing](https://awesome-repositories.com/f/operating-systems-systems-programming/kernel-core-internals/process-and-memory-management/memory-management-systems/multi-modal-memory-routing.md) — Routes incoming text, images, and voice to the specific memory components that require updating. ([source](https://docs.mirix.io/architecture/multi-agent-system/))

### Security & Cryptography

- [Credential Vaults](https://awesome-repositories.com/f/security-cryptography/credential-vaults.md) — Provides a protected vault for the secure storage of sensitive credentials and contacts. ([source](https://docs.mirix.io/architecture/memory-components/))
- [Local Privacy Solutions](https://awesome-repositories.com/f/security-cryptography/local-privacy-solutions.md) — Provides architectural patterns for local-only data storage to ensure user memories remain private and under personal control.
- [Sensitive Data Access Controls](https://awesome-repositories.com/f/security-cryptography/sensitive-data-access-controls.md) — Restricts the retrieval of memories based on security levels to ensure only cleared information is accessed. ([source](https://docs.mirix.io/architecture/search-capabilities/))
- [Data Sensitivity Classifications](https://awesome-repositories.com/f/security-cryptography/sensitive-data-access-controls/data-sensitivity-classifications.md) — Categorizes data by security risk levels to restrict retrieval of sensitive credentials based on permission scopes.

### Software Engineering & Architecture

- [Shared Knowledge Graph Memory](https://awesome-repositories.com/f/software-engineering-architecture/shared-memory-management/shared-knowledge-graph-memory.md) — Integrates a unified memory pipeline across multiple agents to maintain a shared knowledge base. ([source](https://docs.mirix.io))