- Advertisement -
- Google launches Python Adk v.1.0.0 and Java Adk V.0.1.0
- The communication protocol of agent-to-agent has also been improved
- Python SDK for A2A makes it even easier to manage communication between agent
Google has announced a series of updates for his AI agents in the hope that they will be more streamlined as efficient colleagues, rather than tools that colleagues use.
“We see ourselves a future where intelligent agents are not only tools, but also cooperating partners in solving complex challenges, streamlining workflows and unlocking new possibilities,” said product manager Polong Lin and developer Advocate for Cloud AI Holt Skinner in one Blog post.
The latest updates are aimed at improved agent management and improved communication from agent-to-agent-a sign that AI is becoming more autonomous.
Google wants to make AI agents more autonomous
The Tech Giant has improved its agent Development Kit (ADK) with a new production ready and stable V.1.0.0 release of his Python Adk, of which it is already used by Renault Group, Box and Revions. To coincide with this stable release, Google has also confirmed the first release of the Java ADK V0.1.0.
As far as management is concerned, and acknowledges that the Vertex AI agent Engine developers already helps with the implementation, management and scaling of agents in production, Google has also launched his agent Engine UI for agent’s better life cycle management.
The most important characteristics of the new Google Cloud Console onion are a dashboard for managing implemented agents, statistics such as requests and CPU use, session management and tracing and implementation data with error surveys.
Further improvements in the Agent2Agent (A2A) protocol have also been confirmed, including V0.2 which offers stateless interaction support for lightweight communication and standardized authentication with the help of OpenAPI -like schedule. A Python SDK for A2A has also been released to make it easier for developers for integration agent agent communication inside on Python-based agents.
Google wanted to show off the power of A2A and Pochte on support from Auth0, Box AI, MicrosoftSap and Zoom.
“These progress in our ADK, Agent Engine and A2A protocol are designed to offer you an extensive and flexible platform to bring your most ambitious agent-driven projects to life,” said Lin and Skinner.
Maybe you like it too
- Advertisement -