cortex memory
Search and manage the 5-tier memory system. CortexPrism uses a hybrid retrieval approach combining FTS5 keyword search with cosine vector similarity, scored with exponential decay.
Usage
cortex memory search "<query>" # Keyword + vector search (hybrid)
cortex memory search "<query>" --semantic # Vector-only search
cortex memory add "<fact>" # Add a semantic fact
Subcommands
| Subcommand | Description |
|---|
search | Search memory with hybrid retrieval |
add | Add a new semantic memory entry |
Options
| Option | Description |
|---|
--semantic | Use vector-only search (requires embedding provider) |
--tier | Filter results by memory tier |
--limit | Maximum results to return (default: 10) |
--help | Show help for this command |
Memory Tiers
| Tier | Persistence | Content |
|---|
| Episodic (T2) | Session | Turn summaries of user+agent exchanges |
| Semantic (T3) | Long-term | Injected facts and knowledge |
| Reflection (T5) | Permanent | LLM-extracted behavior patterns |
Retrieval Algorithm
Query
→ FTS5 keyword search (episodic + semantic tables)
→ cosine vector similarity (via embedding provider)
→ merge + re-score: score × 2^(-age_days / half_life_days)
→ sort descending → top-K results
Embedding Providers
| Provider | Model | Requirement |
|---|
| OllamaEmbedder | Configurable via Ollama | Ollama running locally |
| OpenAIEmbedder | text-embedding-3-small | OpenAI API key required |
| StubEmbedder | Deterministic hash | No external service needed (default) |
Examples
# Hybrid search (keyword + vector)
cortex memory search "project deployment config"
# Vector-only semantic search
cortex memory search "deployment config" --semantic
# Add a fact to semantic memory
cortex memory add "CortexPrism uses SQLite WAL mode for all databases"