> ## Documentation Index > Fetch the complete documentation index at: https://docs.argentos.ai/llms.txt > Use this file to discover all available pages before exploring further. # Memory Overview > How ArgentOS remembers — MemU is the agent's persistent brain. ## Overview Memory is what separates a personal AI from a stateless chatbot. ArgentOS uses **MemU** (Memory Unit) as its persistent memory system -- a SQLite database with full-text search, significance scoring, and rich metadata that gives your agent long-term recall. Every important fact, preference, event, and relationship your agent learns is stored in MemU and can be recalled across sessions, channels, and time. ## Architecture ```mermaid theme={null} flowchart TD A["Chat + tasks + events"] --> B["MemU (lived experience)"] B --> C["Personal memory recall"] A --> L["LCM (DAG compression)"] L --> M["Compressed history + fresh tail"] D["Uploaded docs / library files"] --> E["RAG ingestion (chunk + embed + ACL)"] E --> F["Knowledge recall (library search)"] G["Contemplation episodes"] --> H["SIS lessons (patterns)"] C --> I["Runtime prompt context"] M --> I F --> I H --> I I --> J["Argent response"] ``` DAG-based context compression — every message stored permanently, searchable even after compaction. Never lose context mid-conversation. Persistent memory — facts, preferences, relationships recalled across sessions, channels, and time. Uploaded knowledge — what was studied. Chunk, embed, ACL-scoped search. Pattern consolidation — what was learned over time. ## How Memory Works ### Storing When the agent encounters important information, it uses the `memory_store` tool to save it: ```json theme={null} { "tool": "memory_store", "input": { "content": "Jason prefers open-source solutions when quality is comparable", "type": "preference", "significance": 8, "entities": ["Jason"] } } ``` Storage can be triggered by the agent automatically (when it recognizes important information) or by the user asking the agent to remember something. ### Recalling When the agent needs context, it uses `memory_recall` to search: ```json theme={null} { "tool": "memory_recall", "input": { "query": "Jason's software preferences" } } ``` MemU searches using FTS5 full-text search, ranks results by relevance and significance, and returns the most relevant memories. ### Bootstrap Injection At session start, ArgentOS also injects relevant memories directly into the system prompt. This gives the agent immediate context without needing to explicitly search. ## Memory Database MemU stores memories in a SQLite database at: ``` ~/.argentos/memory.db ``` The database uses FTS5 (Full-Text Search 5) for fast text search and supports semantic similarity via embeddings. ## Key Concepts | Concept | Description | | ------------------- | --------------------------------------------------------------------------- | | **Significance** | A 1-10 score indicating how important a memory is (higher = more important) | | **Entities** | People, places, and things referenced in the memory | | **Identity fields** | Emotional context, relationships, and personal attributes | | **Embeddings** | Vector representations for semantic similarity search | | **Auto-capture** | The agent automatically stores important information without being asked | ## Deep Dives DAG compression with full recall — grep, describe, expand Database schema, FTS5, embeddings How search and ranking work Rich metadata for nuanced recall MemU + RAG + SIS as one runtime system PostgreSQL and Redis migration architecture Automated deduplication of operational snapshots Experimental observation layer for consolidated knowledge Daily checks + incident triage Consolidation reliability and observability