Google adds open source Agent Executor to support AI agents in production

Google introduced Agent Executor, an open source runtime for running AI agents reliably in production. The runtime targets operational challenges that arise when moving from prototypes to scaled deployments. It supports long-running, distributed workflows that may span minutes to days, include multiple steps, require human input, and need recovery after interruptions. It provides durable execution to resume workflows after outages or approvals, secure sandboxing to isolate components, session consistency controls for distributed execution, and connection recovery to preserve state during network interruptions. It also enables trajectory branching to test alternate execution paths from saved checkpoints. It supports multiple deployment models, including on-prem and managed agent options, and can integrate Google Antigravity, frontier agents, user-built agents, and agents using the Agent2Agent protocol.

"Google has introduced Agent Executor, an open source runtime aimed at helping enterprises run AI agents more reliably at scale, as attention shifts from building agent prototypes to managing the operational challenges of putting them into production."

"For such workloads, the runtime includes support for durable execution, allowing workflows to resume after outages or human approvals, along with secure sandboxing for isolating agent components, session consistency controls for distributed workflows, and connection recovery features intended to preserve execution state during network interruptions, Google wrote in a blog post."

"The runtime also supports "trajectory branching," which allows developers to test alternate execution paths from saved checkpoints without losing prior context, it added."

"Furthermore, Agent Executor bridges multiple deployment models, including on prem and pre-built or custom managed agents, the company said, allowing users to mix and match between any or all of Google Antigravity, frontier agents built by Google, agents built by the user and managed by Google, and custom agents and agents using Agent2Agent (A2A) protocol, as desired."

Read at Computerworld