AI product Open source

Agent Substrate

Agent Substrate is an open-source runtime and control plane for running agent-like workloads at high density. It manages the lifecycle of sandboxed actors, including creation, destruction, suspension, and resumption, and assigns them to a smaller pool of worker pods while routing traffic to the active workers.

View repository Mentioned in 1 video ↓

Overview

The system uses Kubernetes for infrastructure provisioning and pod lifecycle management, with support for sandbox technologies including microVMs and gVisor. It preserves actors' volatile memory and filesystem state through full-state snapshots, enabling sub-second suspend and resume operations and multiplexing many stateful actors across shared infrastructure. It manages standard OCI containers at the kernel level and is designed to support different agent frameworks and harnesses, including ADK-compatible actors, LangChain agents, coding environments, and MCP servers.

Agent Substrate is intended for running agents at scale rather than building them, and its workloads do not have to be literal AI agents. The repository notes that the project is not an officially supported Google product.

What Agent Substrate is used for

1 use taken from transcripts — each links to the moment in the video.

  • An open-source Kubernetes-based system for running agent-like workloads at higher density and lower latency. It multiplexes workloads across worker pods, preserves state while suspending and resuming them, and supports multiple agent frameworks.

Videos mentioning Agent Substrate

1 in the library.