Synapse Layer — Trust Infrastructure for AI Agents

Retrieve relevant persisted memory using semantic, temporal, priority, or hybrid routing. Governance: requires reason (10–200 chars). Rate limit: 20/min.

Persist memory with encryption at rest, sanitization, and deduplication controls.

Extract candidate memories from free-form text with governance filters and sanitization.

Search persisted memory across agent scopes using full-text matching. Governance: requires reason (10–200 chars) because results contain plaintext content.

Check service availability, engine version, and storage health. Public method.

Initialize a persistent memory context for a conversation or agent session. Returns REDACTED metadata by default (detail="summary"). Use detail="full" with a reason (10–200 chars) to retrieve plaintext content under MEMORY_EXPORT_GOVERNANCE_V1.

Save a memory entry to the persistent store. Alias of save_to_synapse.

Store structured memory with metadata and trust scoring.

Recall persisted memory by query. Alias of recall.

List memory metadata with pagination and governance limits.

Submit feedback to adjust trust scoring for stored memories.

Transfer contextual state between agents with continuity controls.

Return uptime and SLO metrics for the MCP service.