Skip to content

About AOS

Agent Observability Standard (AOS) creates industry-wide transparency for AI agents.

Mission

Transform AI agents from black boxes into trustworthy systems through standardized observability.

Enterprises need to see what agents do, understand why they act, and control their behavior. AOS provides the specifications and protocols to make this possible.

What We're Building

Instrumentation Standard: AOS standard for agent instrumentation.

Standards Extensions: Enhance CycloneDX, SPDX, SWID for AI agent components. Extend OCSF and OpenTelemetry with agent-specific schemas.

Protocol Integration: Standardize instrumentation hooks for agent platforms. Enable Guardian Agents through A2A communication. Extend MCP with observability capabilities.

Reference Implementations: Deliver working examples on popular platforms like CrewAI. Provide clear patterns for OCSF and OpenTelemetry integration.

Community Adoption: Build with the community. Open standards, open implementations, open collaboration.

Join the Mission

AOS succeeds when the entire AI agent ecosystem adopts these standards. We're building this together.

  • Contribute: Help shape the specifications
  • Implement: Build AOS support in your agent platform
  • Advocate: Spread the word about trustworthy agents

Contact us at [email protected].