Memory
Get agent memories
Retrieve long-term memories for a specific agent.Search by context
Find memories relevant to the agent’s current situation. This is the most powerful retrieval method — it matches the current goal and environment against past episodes.Claims (semantic knowledge)
Search claims
Query extracted facts using natural language. Claims are atomic pieces of knowledge like “User prefers Sci-Fi” or “Seat H12 was unavailable.”Keep the
query_text natural. Don’t include IDs in the string — filter the results in your application code instead.Strategies
Get agent strategies
Retrieve learned behavioral patterns for an agent.Find similar strategies
Search for strategies that match a given set of goals or tools. Use this to share wisdom between agents.Get action suggestions (Policy Guide)
Ask the system “What should the agent do next?” based on the current context.Graph exploration
Get graph structure
Get context-anchored subgraph
Query nodes by properties
Traverse relationships
Next steps
Query selection guide
Learn which search method to use for every situation.
Sidecar intent parsing
Extract structured intents from LLM responses locally.
