AgentCrypt: Advancing Privacy and (Secure) Computation in AI Agent Collaboration

LLM-based agents are inherently probabilistic and ill-suited for security-critical tasks, especially in applications handling sensitive data where privacy risks often arise after access is granted. We present AgentCrypt, a framework that prioritizes privacy over correctness by addressing post-access leakage through tool calls, memory, and derived outputs. AgentCrypt introduces a three-tier architecture for fine-grained, privacy-preserving multi-agent workflows and provides formal security guarantees for tagged data. It integrates seamlessly with existing platforms, demonstrated through implementations with LangGraph and Google ADK, while remaining platform-agnostic.