Google launches open-source runtime for AI agents

AX is an open source project for managing and executing complex AI agent environments across multiple systems. It coordinates agent workflows, logs executions, and enables communication between local and remote components. The platform targets reliability, including recovery when processes fail or are interrupted. AX supports resumption so AI processes can continue automatically after failures, including in distributed setups where agents, tools, and skills run as separate components. An event log stores execution status, and a single-writer architecture keeps a central controller responsible for consistent state management. AX is designed for long-running workflows that may require handling human input, network interruptions, or system errors over minutes, hours, or days, using durable execution. It also includes secure sandboxing, session consistency controls, and connection recovery to maintain execution status during network outages.

"Google has announced a new open source project called AX, short for Agent Executor. The project focuses on managing and executing complex AI agent environments that run across multiple systems and perform long-running tasks. According to Google, AX is intended as a distributed agent runtime. The platform is designed to coordinate agent workflows, log executions, and facilitate communication between local and remote components. The emphasis is on reliability and recovery capabilities when processes fail or are interrupted."

"A key feature of AX is support for so-called resumption. This allows AI processes to automatically resume after failures or interruptions. According to Google, this also applies to complex distributed environments where various agents, tools, and skills run as separate components. To achieve this, the project uses, among other things, an event log where the execution status is stored. Additionally, Google mentions a single-writer architecture in which a single central controller remains responsible for consistent state management."

"According to Google, AX is specifically designed for so-called long-running workflows: AI processes that can remain active for minutes, hours, or even days and must be able to handle human input, network interruptions, or system errors in the meantime. To this end, the platform supports features such as durable execution, which allows workflows to retain their status and continue after interruptions. In addition, Google highlights features such as secure sandboxing to isolate agent components from one another, session consistency controls for distributed workflows, and connection recovery to maintain execution status during network outages."

"AX is currently still in an early development phase. Google warns that key parts of the architecture and runtime are still subject to change, meaning future versions will likely not remain compatible with earlier implementations. AX is currently still in an early development phase. Google warns that key parts of the architecture and runtime are still subject to change, meaning future versions will likely not remain compatible with earlier implementations."

Read at Techzine Global