About SAMP
Learn about SAMP, its purpose, protocol scope, current Internet-Draft status, participation model and author.
About SAMP
The Simple Agent Management Protocol (SAMP) is an experimental, vendor-neutral management-plane protocol for heterogeneous AI agents.
SAMP defines a common operational interface through which a management system can discover and enroll agents, inspect their state and capabilities, receive operational events, subscribe to event streams, apply controlled configuration, and invoke explicitly exposed operations under policy control.
Why SAMP exists
AI-agent ecosystems are rapidly developing protocols for communication, collaboration, task delegation, tool access, and context exchange. These capabilities do not, by themselves, provide the operational management plane required to govern heterogeneous agents throughout their lifecycle.
Operators still need consistent ways to answer practical questions:
- Which agents exist in the environment?
- What identities, capabilities, tools and resources do they expose?
- Are they healthy, trusted and operating within policy?
- How can configuration be applied safely?
- How should events, state changes and operational failures be reported?
- Which actions may a management system invoke, and under what controls?
SAMP is intended to provide a common protocol foundation for addressing these operational requirements.
Scope and boundaries
SAMP is not an agent-to-agent communication protocol, an agent framework, or an agent tool-use protocol.
It is designed to complement technologies such as A2A and MCP by addressing a separate protocol relationship: operational management and control between a management system and managed AI agents.
SAMP also draws from established network and service-management principles, while introducing concepts specific to AI-agent environments, including dynamic profiles, autonomy classes, enrollment, trust states and policy-gated execution.
Current status
SAMP version 0.1 is published as an individual Internet-Draft with an intended Experimental status:
https://datatracker.ietf.org/doc/draft-efstathiou-samp-agent-management/
The initial version is intended for technical review, controlled implementations and independent interoperability testing.
This is an individual Internet-Draft. It is not endorsed by the IETF and currently has no formal standing in the IETF standards process.
Participation
Technical review, operational use cases, security analysis, experimental implementations and interoperability testing are welcome.
Contact:
Author
SAMP was initiated and authored by Stelio E. Efstathiou, an independent network, security and infrastructure architect with more than three decades of experience in carrier, datacenter, enterprise and European institutional environments.
The project was publicly launched in August 2026 as an open technical effort toward interoperable operational management of heterogeneous AI agents.