Agent Executor, Google’s distributed Agent Runtime

Own your agents, models, and compute

With Agent Executor, enterprises have maximum flexibility to maintain sovereignty over workloads and keep proprietary workflows within their self-managed compute and custom sandboxes. Your internal development teams have much more flexibility over how agents are deployed and managed and you benefit from:

• Prevent vendor lock-in: Deploy your agents on your own infrastructure without being tethered to a specific provider’s model or compute environment. This allows for full control over data residency and your cost and budgetary controls.

• Bring your own harness and agents: Agent Executor is designed to be harness-agnostic, allowing you to bring your own or use those made available by other vendors. It also supports agents developed with industry-standard frameworks and protocols providing a broad ecosystem of compatible agents.

• Fully control execution: Agent Executor allows developers to run the entire agentic stack, including MCPs, skills, and other agents, directly on their own data plane. Developers can choose any compute with custom isolation boundaries and workload policy enforcement.

Scale agents up on Kubernetes with an agent-first compute layer

As agent workloads scale into the hundreds of millions and become increasingly long-running, our customers are hitting the limits of traditional compute abstractions because unlike traditional software, agents are nonlinear programs that wait for external inputs. To solve this problem, we’ve partnered with the Google Kubernetes Engine team on Agent Substrate, a new open-source project also announced today.

Agent Substrate introduces a new level of abstraction for Kubernetes that moves agents onto and off of ready compute capacity in real-time, resulting in lower latency with higher scale and efficiency. While standard Kubernetes is optimized to handle thousands of long-running services, Agent Substrate is designed for the chatter of millions of sub-second tool calls that would otherwise overwhelm a standard control plane. Agent Substrate takes core secure runtime and snapshotting capabilities of existing sandbox infrastructure and pairs them with a minimal control plane designed to bypass some of the limitations of Kubernetes, without reinventing the rest of it. Working together, these layers enable you to:

• Maximize compute efficiency: Agent Substrate introduces a new control plane designed to handle hundreds of millions of registered agents. Together with Agent Executor, Agent Substrate can provide a foundation for today’s largest agent deployments.

• Stay within the Kubernetes ecosystem: Agent Substrate is built on top of Kubernetes and allows scheduling and horizontal scaling of compute with declarative configuration.

In the demo below, we showcase using Agent Executor together with Agent Substrate with a sample workload.