ANX: Protocol-First Design for AI Agent Interaction with a Supporting 3EX Decoupled Architecture

ANX is a new protocol-first framework designed for AI agent interaction, featuring a 3EX decoupled architecture that reduces token consumption by up to 66% compared to existing methods. The open-source protocol addresses security and efficiency issues in current AI agent implementations through agent-native design and integrated CLI, Skill, and MCP components.

• →ANX protocol reduces token consumption by 47-66% compared to MCP-based skills and GUI automation in testing with Qwen3.5-plus and GPT-4o.
• →The framework introduces agent-native design with high information density and flexibility to eliminate interaction inconsistencies.
• →ANX features built-in security with LLM-bypassed UI-to-Core communication and human-only confirmation systems.
• →The protocol supports on-demand lightweight apps without pre-registration and machine-executable SOPs for multi-agent collaboration.
• →Execution time is reduced by approximately 58% compared to MCP-based skills according to experimental validation.