MEMORY TYPES
Six types of memory for agents
Human cognition uses multiple memory systems. Agents benefit from the same separation. Spectron maps each to structured storage with graph relationships and temporal awareness: working memory for active session context, semantic memory for facts and knowledge graphs, episodic memory for past interactions and outcomes, procedural memory for learned patterns and workflows, preference memory for user personalisation, and shared memory for multi-agent coordination.
AUTONOMOUS UNDERSTANDING
Memory that keeps thinking
Most memory systems are passive. They store what agents tell them and retrieve what agents ask for. Spectron's memory is active - background processes autonomously discover connections between entities, consolidate fragmented knowledge, and infer relationships that no single conversation could reveal.
THE PROBLEM
The fragmented memory tax
Memory middleware like Mem0 layers a memory API on top of external databases - a vector store here, a key-value store there, maybe a graph database for relationships. Every layer adds latency, failure modes, and consistency gaps.
THE SOLUTION
Atomic context with Spectron
Spectron runs on SurrealDB. Memory, knowledge graphs, vectors, and structured data share the same ACID transaction boundary. No middleware, no glue code, no consistency gaps.
FREQUENTLY ASKED QUESTIONS
