Store a fact, note, or piece of information in SharedMemory. The memory pipeline will classify it, check for conflicts, extract knowledge, and build the graph automatically.

Retrieve context BEFORE answering. Searches SharedMemory for relevant memories using semantic similarity. Returns matching memories from vector search + related knowledge graph facts.

Get everything SharedMemory knows about a specific entity (person, project, concept, etc). Returns the summary, all facts, and relationships.

Search for entities in the knowledge graph by name. Useful for finding people, projects, concepts, etc.

Get an overview of the entire knowledge graph for a volume. Shows all entities and their relationships — like a map of everything SharedMemory knows.

List all memory volumes (projects) this API key has access to. Each volume is an independent memory space.

Delete an existing memory by ID.

Update the content of an existing memory by ID.

Submit feedback on a memory's relevance. Helps improve future recall quality.

Store multiple facts or pieces of information at once. More efficient than calling remember() in a loop.

Retrieve a specific memory by its ID. Useful for viewing the full details of a memory found via recall.

Get a comprehensive profile for a volume or user. Returns categorized facts (identity, preferences, expertise, projects), relationships, recent activity, instructions, topics, stats, and a pre-formatted context_block for LLM injection.

Assemble a smart context block from stored memories. Returns a pre-formatted context string ready to inject into a system prompt.

List all documents that have been uploaded and processed for a volume.

Store a persistent instruction or rule for a volume. Instructions are automatically included in every context assembly — any agent querying this volume will see them. Use for coding conventions, project rules, team preferences, or architectural decisions that all agents should follow.

Ask SharedMemory to make a decision or answer a question based on all stored knowledge. Returns an answer with confidence score, supporting evidence, applicable procedures, and conflict detection. Use this when you need a definitive answer about 'what should we do?' or 'how do we handle X?'

Get a structured profile for any entity (person, project, team, concept, company). Returns their role, facts, relationships, recent activity, and confidence level. Use this to understand 'who is X?' or 'what is project Y?'

List all active instructions/rules for a volume. These are automatically included in every context assembly.