OpenAI releases new agent framework for developers

New Course: ACP: Agent Communication Protocol Learn to build agents that communicate and collaborate across different frameworks using ACP in this short course built with @IBMResearch's BeeAI, and taught by @sandi_besen, AI Research Engineer & Ecosystem Lead at IBM, and pic.x.com/ykhi6eHH8N

OpenAI launched Priority processing today for Enterprise API customers offering predictably low latency and reliable high-speed performance with 99.9% uptime SLA at premium pricing relative to Standard processing rates using flexible pay-as-you-go basis instead of requiring pic.x.com/WOCQcoNdnr

Github 👨‍🔧: Flexible framework for managing multiple AI agents and handling complex conversations 6.1K github stars - Smart query routing based on context - Python & TypeScript support - Handles streaming & non-streaming responses - Maintains context across agents - Easy agent pic.x.com/l6tfu0n9zA

Google’s Approach to AI Agent Security AI agents act on their own, so a mistake or a tricked prompt can cause real-world harm. Google lays out a double safety net: hard coded rules stop dangerous commands, and an extra layer of AI checks the grey areas. The paper warns that pic.x.com/R2zSALyd4H