BlueprintsAI Agent SandboxOverview

AI Agent Sandbox Blueprint

The AI Agent Sandbox blueprint defines the template for isolated agent sandbox service instances on Tangle. Operators run the sandbox runtime and sidecar containers. Users create sandboxes, trigger workflows, attach terminals, inject secrets, and inspect execution through the hosted app.

Source repo: https://github.com/tangle-network/ai-agent-sandbox-blueprint

Product Shape

AreaSource-backed behavior
Cloud modeMulti-tenant fleet; callers create and delete sandboxes on demand through on-chain jobs.
Instance modeOne sandbox per service instance; the operator auto-provisions on startup and reports lifecycle directly.
TEE instance modeDedicated instance with TEE attestation and sealed secrets.
Hosted apphttps://agent-sandbox.blueprint.tangle.tools/
Metadata identitypublisher.namespace = "tangle", requestedSlug = "ai-agent-sandbox"

On-Chain Jobs

IDJobModeWhat it does
0SANDBOX_CREATECloudCreates a sandbox container, microVM, or TEE-backed sandbox.
1SANDBOX_DELETECloudDeletes the sandbox and releases runtime resources.
2WORKFLOW_CREATECloud and instanceRegisters a workflow template.
3WORKFLOW_TRIGGERCloud and instanceStarts a registered workflow.
4WORKFLOW_CANCELCloud and instanceCancels active workflow execution.

JOB_WORKFLOW_TICK is internal cron-driven workflow progress. It is not a public on-chain job.

PageUse it for
Operator RequirementsHost sizing, env vars, Docker, Firecracker, TEE, ports.
Runtime and HarnessesSidecar capabilities, harness discovery, secrets, auth, runtime safety.
Dapp and IndexerMetadata, iframe policy, indexed events, service state.

Source Material

This page is based on the blueprint repo’s README.md, docs/runbook.md, metadata/blueprint-metadata.json, ai-agent-sandbox-blueprint-lib/src/lib.rs, sandbox-runtime/src/operator_api.rs, and TEE-GUIDE.md.