SQLite Memory
Zero-cost local memory system using SQLite. No API keys, no cloud calls, no vector embeddings. Just fast, reliable local storage.
Quick Start
from sqlite_memory import store_preference, store_decision, search_memory, get_memory_stats
# Store a preference
store_preference("User dislikes overly apologetic language", importance=1.0)
# Store a project decision
store_decision("Using pygame.mouse for head motion simulation", importance=0.9)
# Search memories
results = search_memory("sensitivity")
# Returns: [{id, category, content, importance, created_at}, ...]
# Get stats
stats = get_memory_stats()
# Returns: {total_memories, categories, db_path}
When to Use
| Scenario | Function |
|---|---|
| User corrects you | store_correction() |
| User expresses preference | store_preference() |
| Important decision made | store_decision() |
| Project milestone reached | store_project_update() |
| Need to recall past context | search_memory() |
Memory Categories
- preference — User likes/dislikes, style preferences (importance: 0.7-1.0)
- decision — Technical choices, design decisions (importance: 0.8-0.9)
- fact — General facts about user or project (importance: 0.5-0.7)
- project — Project-specific updates, milestones (importance: 0.7-0.9)
- correction — Explicit corrections from user (importance: 1.0)
API Reference
Storage Functions
store_preference(content: str, importance: float = 0.8) -> int
store_decision(content: str, context: dict = None, importance: float = 0.9) -> int
store_fact(content: str, importance: float = 0.6) -> int
store_project_update(project: str, content: str, importance: float = 0.7) -> int
store_correction(content: str, importance: float = 1.0) -> int
Retrieval Functions
search_memory(query: str, category: str = None, limit: int = 10) -> List[dict]
get_memory_stats() -> dict
Architecture
workspace/
└── memory.db # SQLite database
├── memories # Main memory table
│ ├── id # Auto-increment
│ ├── category # preference/decision/fact/project/correction
│ ├── content # The actual memory text
│ ├── context # Optional JSON metadata
│ ├── importance # 0.0-1.0, affects sort order
│ ├── created_at # Timestamp
│ └── access_count # Usage tracking
└── sessions # Session tracking (optional)
Comparison with Other Systems
| Feature | sqlite-memory | graph-memory | elite-longterm-memory |
|---|---|---|---|
| Cost | Free | API fees | API fees (OpenAI) |
| Setup | Zero config | Needs API keys | Needs LanceDB + OpenAI |
| Speed | Instant (local) | Network calls | Vector search |
| Complexity | Simple | Complex (graph + LLM) | Complex (6 layers) |
| Best for | Quick recall, preferences | Deep knowledge graphs | Enterprise agents |
Limitations
- Text search only — No semantic/vector search (use graph-memory if needed)
- Single user — No multi-user isolation
- No auto-extraction — Must manually call store functions (unlike Mem0)
Migration Path
If you outgrow sqlite-memory:
- Need vector search? → graph-memory with Ollama (local embedding)
- Need auto-extraction? → Mem0 + OpenAI API
- Need cross-device sync? → elite-longterm-memory + SuperMemory cloud
Resources
- scripts/sqlite_memory.py — Core memory module, import and use directly
- references/usage.md — Detailed usage examples and patterns
