Tag
A developer highlights the difficulty of tracking AI agents and non-human identities in modern environments, noting that many agents spin up and disappear without visibility.
Discusses the challenge of managing identity for agents dynamically spawned by an orchestrator at runtime, a key concern in multi-agent systems.
AWiki upgrades from a Skill to an open-source infrastructure product for AI agent connectivity, enabling internal and cross-domain collaboration with W3C DID-based identity, end-to-end encryption, and multiple integration methods.
The Enterprise-Managed Authorization extension for MCP is now stable, allowing organizations to centrally manage authorization for MCP servers and enabling zero-touch OAuth for end-users. Adopted by Anthropic, Microsoft, and Okta.
NewCore emerges from stealth with $66M to provide an identity and access management platform specifically designed for AI agents, treating them as first-class identities alongside human employees.
Satya Nadella advocates treating AI agents as employees with identities, permissions, and audits, and discusses Microsoft's tools for managing them.
The article discusses Avatar.inc's approach to building 'Agentic Twins' by layering a trust protocol with Decentralized Identifiers (DIDs) over the OpenClaw runtime to solve agent verifiability.