Idapixl Cortex

Choose this endpoint when your AI agent needs to maintain a coherent, non-redundant long-term memory — especially when ingesting new information that may overlap or conflict with prior knowledge. Ideal for agents that accumulate facts over time and need to avoid belief drift or duplicate storage. Prefer this over generic vector stores when semantic deduplication and logical consistency checking are both required in a single call.

• Memory graph not initialized — agent must establish a session before querying
• Input content too ambiguous for semantic matching — returns low-confidence novelty score
• Contradiction detection may produce false positives on semantically similar but logically distinct claims
• Rate limiting or micropayment failure via x402 on Base network
• Empty or malformed belief statement returns validation error