“Be ready for change”: AAIF’s CTO on why the agent stack won’t settle
If you’ve spent any time over the past year trying to get AI agents to talk to each other without The post “Be ready for change”: AAIF’s CTO on why the agent stack won’t settle appeared first on The New Stack .
The Agentic AI Foundation (AAIF), backed by the Linux Foundation, is addressing the struggles developers face when trying to get AI agents to communicate with each other without causing architecture issues. The push for a standardized agent stack began shortly after the foundation launched in December 2025, with key projects like the Model Context Protocol (MCP), Agent Skills, Open Responses, OpenEnv, and OpenSandbox joining the fold.
AAIF's CTO, Manik Surtani, emphasized the importance of vendor neutrality and standardization in AI agent interoperability. Projects like Agent Skills from Anthropic, Open Responses from OpenAI, OpenEnv from Hugging Face, and OpenSandbox from Alibaba are expected to bring more flexibility and trust to the agentic AI stack. Surtani encourages developers to be ready for change as the stack evolves rapidly, noting that agent memory and context management remain critical challenges.
The new Sandbox lifecycle phase was introduced to accommodate early-stage, high-momentum community tools before they reach large-scale enterprise use.
Written by urgent.news from The New Stack's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.