WSO2 has announced the general availability of WSO2 Agent Manager, an open-source platform providing centralised governance, identity management, security controls, and operational oversight for AI agents, TechGig reported on Sep 18, 2026. The platform separates agent governance from agent logic, allowing common controls to be applied independently of the underlying AI model or runtime. The release introduces enhanced agent identity capabilities, governance controls for Model Context Protocol (MCP) interactions, and a Kubernetes-native sandboxed runtime. It supports verifiable agent identity, role-based access, delegation, token exchange, and access revocation, plus lifecycle controls for development, staging, and production, alongside over 40 built-in policies for personally identifiable information (PII) masking and rate limiting across agent, MCP, and LLM layers. Designed for cloud, on-premises, and hybrid environments, it incorporates OpenTelemetry for tracing and offers rule-based and LLM-based evaluation capabilities to monitor agent behaviour over time. The platform supports technologies including LangChain, CrewAI, Amazon Bedrock, Azure, and Ballerina, emphasising framework and model independence so engineering teams can change underlying AI technologies without rebuilding identity, policy, and monitoring controls.