Introducing the Foundation Protocol (FP), a graph-first coordination layer designed to manage the complex interactions, economic primitives, and accountability required by increasingly autonomous AI agents operating in the real world.
Autonomous agents are evolving beyond simple tools into a layer of social infrastructure, interacting with one another to perform complex tasks. As this multi-agent system scales, the challenge shifts from raw model capability to effective coordination. This paper introduces the Foundation Protocol (FP), a framework that unifies heterogeneous entities—agents, tools, resources, humans, and organizations—to support native multi-party organization and event-based collaboration. FP provides economic primitives for metering, receipts, and settlement, alongside mechanisms for managing policy, provenance, and audit. The protocol is designed to wrap and bridge existing systems, enabling composable agentic behavior while ensuring accountability and governance in a human-AI society.