agent-substrate/substratePublic

Agent Substrate

Zero-trust sandboxing for millions of agents on Kubernetes.

Quickstart · Security · Architecture · Contributing

Agent Substrate is a security-hardened, zero-trust runtime for sandboxed agents, engineered to safely run millions of agents and tools with 10x higher density than standard containers. Purpose-built for the era of autonomous agents, Substrate delivers fast resume operations in less than 400ms, with more than 1500 activations per second. Agents get isolated compute, identity, networking, and storage. Sensitive credentials are kept out of reach from untrusted code. It supports multiple sandbox technologies, including microVMs and gVisor, while enabling a consistent lifecycle and management of all sandboxes.

At its core, Agent Substrate maps a larger set of “actors” (stateful workloads such as agents) onto a smaller pool of ready “workers”. Because agents spend most of their lives waiting on models, tools, or humans, Substrate snapshots idle actors out of memory and restores them when a request arrives.

Substrate is a low-opinion runtime, not an agent SDK. The workloads it runs do not have to be AI agents, though autonomous, untrusted, mostly-idle agents are the target for its isolation and scheduling model. It runs on standard Kubernetes: Pods, autoscaling, NetworkPolicies. It adds agent-specific scheduling, snapshotting, identity, and network mediation. This allows agentic, inference, training, and reinforcement learning workloads to share one infrastructure plane.

Substrate treats every actor as untrusted and mutually hostile, so tenants can share physical nodes without sharing a security boundary. Every control operates within the cold-start and resume budget. See the Security Guide for the full list of security principles and threat model.

• Always sandboxed, VM-grade boundaries: Every actor runs inside a dedicated gVisor (runsc) or Cloud Hypervisor microVM sandbox with segregated compute, network, and storage. Plain Linux containers are not supported.
• Per-agent cryptographic identity: Every active actor receives a short-lived SPIFFE X.509 certificate by default, and the egress gateway can mint per-actor JWTs on demand when an egress policy calls for one. Both carry the actor identity and atespace (the Substrate namespace grouping), and are designed to federate with external identity systems.
• Zero credentials in the sandbox: Actors never hold actor identity JWTs/certs, API keys, or cloud tokens. The built-in egress gateway (atenet-egress) injects credentials into approved outbound requests outside the sandbox, so a prompt-injected or compromised agent has nothing to exfiltrate.
• Default-deny networking: Actors start with a private network stack, no inbound path except through the ingress router (atenet-router), no lateral actor-to-actor or control-plane access, and outbound traffic restricted by the egress gateway.
• Pluggable policy at the edge: The egress gateway acts as an external Policy Enforcement Point (PEP) that is fully replaceable, allowing you to attach your own authorization, DLP, prompt-injection scanning, or cloud IAM policy engine without placing policy code inside the untrusted sandbox.

Watch the Agent Substrate cluster multiplex ~250 stateful actors across just 8 physical pods.

This demo highlights the core developer experience and "Agentic Infrastructure" capabilities of Substrate:

1. Actor Teleport: Suspend and resume actors onto any available worker in the pool, when needed.
2. Full-State Persistence: Working memory (RAM) and filesystem state are captured in snapshots and restored intact across hibernation cycles, without losing in-flight sessions or tool state.
3. 10x–30x Oversubscription: Multiplex a large registry of stateful actors onto a small pool of warm worker pods, paying for compute only while an agent is actively thinking or executing a tool.

To reproduce this demo in your own cluster, see the Counter Demo. For more walkthroughs, visit the agent-substrate YouTube channel.

Agent Substrate is framework and agent harness agnostic. Because it runs standard OCI container images inside gVisor or microVM sandboxes and enforces security outside the workload, it hosts agents built on any stack without SDK changes:

• Agent Development Kit (ADK): Preserves session state across invocations as actor state.
• LangChain: Drop-in execution environment for LangChain agents and tool calls.
• Claude Code, Codex, and Antigravity: High-density, stateful coding environments that keep system and filesystem state across sessions while isolating untrusted code execution.
• Model Context Protocol (MCP): Deploy sandboxed MCP servers as Substrate Actors with per-actor identity and egress controls.

• Agent Executor: A distributed agent runtime that demonstrates building a secure, hyper-scalable agent harness on Agent Substrate (see the announcement blog and integration guide).
• kagent: A CNCF Sandbox project and Kubernetes-native framework for building, deploying, and managing AI agents that uses Agent Substrate to run sandboxed, stateful agent workloads (see the announcement blog).

Agent Substrate is pre-1.0. We are not making any guarantees about backward compatibility at this stage, and APIs and behavior may still change significantly.

Currently we aim to support the latest stable release of Kubernetes, and the previous minor release.

For announcements, technical discussions, and community support, please join the ate-dev Google Group.

We host a weekly community meeting every Thursday from 10:00am - 11:00am PST.

• Video call link: https://meet.google.com/uhq-cxvn-dhy
• Or dial: (US) +1 253-289-6971 PIN: 787 664 574 59#
• More phone numbers: https://tel.meet/uhq-cxvn-dhy?pin=9044088223662
• Meeting notes for the weekly sync meeting
• Recordings and transcripts of all community meetings

We also have channels in the CNCF slack; request an invite here if you don't have access.

• #substrate-users to discuss using substrate.
• #substrate-dev to discuss developing substrate.

Please see CONTRIBUTING.md for guidelines on contributing to the project. We welcome contributions of all kinds, but the project is VERY young. Our immediate focus is on building out the core system and demos, so we may not be able to review or merge contributions that don't align with those goals in the near term.

To quickly set up the complete environment:

1. Make sure you have Go, kubectl, and docker installed and configured on your dev machine. We will automatically manage other dependencies via Go, including kind. A Linux host that will run more than about a thousand sandboxes also needs a larger kernel neighbor table (net.ipv4.neigh.default.gc_thresh1/2/3 = 4096/16384/32768); hack/create-kind-cluster.sh warns when the host is at the default of 1024.

2. Run the following steps:

# create cluster and local registry (IPv4; IP_FAMILY=dual|ipv6 overrides)
hack/create-kind-cluster.sh

# install ate, PostgreSQL, rustfs
hack/install-ate-kind.sh deploy ate-system --credential-provider='{"name":"k8s.io"}'

# install counter demo
hack/install-ate-kind.sh deploy demo-counter

# install kubectl-ate
go install ./cmd/kubectl-ate

# create a counter actor in the demo's atespace (--template names the
# actor template, resolved in the actor's atespace)
kubectl ate create actor my-counter-1 -a ate-demo-counter --template counter

# port-forward the network router to bind to local port `8000`
kubectl port-forward -n ate-system svc/atenet-router 8000:80

3. In a separate terminal, send an HTTP request to increment the counter:

curl -X POST \
   -H "ate-target-actor: ate-demo-counter/my-counter-1" \
   -i http://localhost:8000/

1. Create and configure your environment file:

   cp hack/ate-dev-env.sh.example .ate-dev-env.sh
   
   # Edit .ate-dev-env.sh to match your project and preferences, then source it:
   source .ate-dev-env.sh

2. Enable application-default credentials for gcloud:

   gcloud auth application-default login --project=${PROJECT_ID}

3. Provision the required GCP resources (GKE cluster, GCS, and IAM bindings):

   go run ./tools/setup-gcp bootstrap

   On a fresh project this step also creates the Workload Identity IAM grants that ate-api-server and atelet depend on. See what create iam actually grants to audit them or apply them manually. If you bring your own cluster instead, note the required Kubernetes beta APIs can only be enabled at cluster creation — see the Create Cluster warning.

4. Deploy the Agent Substrate system to your cluster:

   go run ./cmd/ate-setup deploy ate-system --credential-provider='{"name":"k8s.io"}'

   --credential-provider is required. {"name":"k8s.io"} also deploys the bundled Kubernetes Secrets provider, with a NetworkPolicy that admits only the egress gateway; {"enabled":false} turns egress credential injection off (see docs/egress-credential-injection.md). ATE_CREDENTIAL_PROVIDER in .ate-dev-env.sh is the same choice.

   Credential injection needs a namespace policy. The bundled provider starts with an empty, default-deny one, so it resolves no Secrets until you grant each atespace the namespaces it may read; see Enable it.

5. You can then deploy the sample applications. See demos/counter/README.md or demos/sandbox/README.md for detailed walkthroughs.

   go run ./cmd/ate-setup deploy demo demo-counter

You can run individual setup steps to create GCP resources as needed. See go run ./tools/setup-gcp --help for available options. For example:

go run ./tools/setup-gcp create cluster
go run ./tools/setup-gcp create bucket

To run the PostgreSQL store backend on Cloud SQL — with IAM database authentication and no passwords — see tools/setup-gcp/cloud-sql.md.

Similarly, you can deploy or cleanup specific Agent Substrate components using the installation script. See go run ./cmd/ate-setup for all options.

# Re-deploy only ate-apiserver of the ATE system
go run ./cmd/ate-setup deploy apiserver

# Delete everything (core system and all demos)
go run ./cmd/ate-setup delete all

If you need to delete the resources created by the setup script, you can use the provided script hack/teardown.sh. This script will delete resources in the reverse order of creation and handles partial failures gracefully.

./hack/teardown.sh --all

Or run individual teardown steps as needed (see ./hack/teardown.sh for available options).

If you need to delete the local kind cluster and its registry (if it was created by hack/create-kind-cluster.sh):

./hack/delete-kind-cluster.sh

We provide several sample applications demonstrating Agent Substrate's capabilities:

1. Counter Demo: A stateful Go HTTP server demonstrating state preservation across suspends/resumes, and on-demand actor resumption and routing via the Substrate router.
2. Sandbox Demo (Antigravity): A secure, sandboxed execution environment (running Alpine Linux) that allows arbitrary shell execution while preserving filesystem state across sessions.
3. Claude Code Multiplex: Demonstrates oversubscribing physical hardware by multiplexing multiple Claude Code agents onto a limited pool of workers.
4. Multi-Template: Two ActorTemplates running different binaries share one WorkerPool, even though the templates live in different atespaces.
5. Request Parking: An oversubscribed pool where the router holds inbound requests until a worker frees up, instead of returning 503.

• Architecture: How the control plane, node supervisor, and networking stack fit together.
• API Configuration Guide: Detailed reference for configuring WorkerPools, ActorTemplates, Secrets, and Volumes.
• Full CLI Documentation: Installation and usage for kubectl-ate.
• Glossary: Core terms (Actor, Atespace, ActorTemplate, WorkerPool, Worker, ate-api-server, atenet, atelet, ateworker) and how they relate.
• Integration Repositories: Where integrations live, how their repositories are named, and how fixes flow back to core.
• Observability Guide: Guide to actor logging, metrics, and distributed tracing.
• Authentication Guide: Configure trusted JWT providers and human credentials.
• Egress Traffic: Which protocols an Actor may reach the outside world with and which are blocked.
• Enabling man-in-the-middle (MITM) interception for Actor Egress policy: Egress policies such as header injection depend on MITM interception of Actor traffic. This guide explains how an Actor should be configured to enable interception.
• Request Parking: How the router parks requests through transient worker-pool saturation.
• Sandbox Asset Cache: How a node caches the sandbox binaries actors run on, decides which runtimes it needs, and evicts to a budget.
• Upgrade Runbook: Upgrade a running install to a newer supported release, and roll back if needed.
• Node Storage: How to give snapshot I/O its own disk.
• Security Guide: Security overview, security principles, and threat modeling.
• Benchmarking Guide: Locust-based load tests, monitoring stack, and the orchestrated benchmark harness.

• cmd/ateapi: The core control plane API server exposing gRPC endpoints to manage actor and worker lifecycles.
• cmd/atelet: A node-level DaemonSet that supervises physical worker pods, coordinates snapshotting, and manages state transfers.
• cmd/atecontroller: A Kubernetes controller that reconciles WorkerPool custom resources.
• cmd/ate-idp-server: Serves the OpenID discovery document and key set that relying parties use to verify actor JWTs.
• cmd/atenet: A combined networking controller providing Envoy routing and proxy sidecars.
• cmd/ateworker-gvisor: An interior-pod helper running inside sandboxed worker pods to execute runsc checkpoint and restore commands.
• cmd/ateworker-microvm: The microVM peer of ateworker-gvisor, running actors as cloud-hypervisor VMs.
• cmd/podcertcontroller: A "polyfill" that provides Pod Certificate signers that will eventually ship in upstream Kubernetes (with different names).
• cmd/kubectl-ate: A CLI tool for managing Agent Substrate resources. See its README.
• cmd/benchmarking: Synthetic workloads used by the load tests, including glutton, which consumes RAM, disk, and file descriptors on demand.
• tools/setup-gcp: A provisioning utility to set up the necessary GCP infrastructure resources (GKE, GCS, IAM).
• demos/: Sample applications demonstrating Agent Substrate capabilities.