Agent SDKs
Typed execute endpoint
Agent SDKs provide a typed execute endpoint with per-agent credentials. Each agent operates under its own identity and policy scope.
The governance layer that sits in front of the webhooks your AI agents call. Policy gates, approval workflows, atomic bundles, and OTEL traces — before any action executes.
Works alongside any orchestration runtime — Google ADK, LangChain, CrewAI, AutoGen, or custom. This is the governance layer, not the runtime.
Agent SDKs provide a typed execute endpoint with per-agent credentials. Each agent operates under its own identity and policy scope.
Enforce spend limits, throughput caps, and payload validation before any agent action executes. Non-conforming requests are blocked with a clear reason.
Group multiple agent actions into a single bundle. If any step fails, preceding steps are rolled back automatically.
Require human approval before sensitive actions proceed. Every execution is recorded as an OTEL trace for full auditability.
Duerelay ACP is the governance layer between your agent runtime and the systems it acts on. Bring your own orchestration framework — we govern the actions.
Google ADK, LangChain, CrewAI, AutoGen, Bedrock Agents, or custom
Policy gates · approvals · bundles · OTEL traces
Payments, CRM, internal APIs, partner integrations
The Agent Control Plane ships with Duerelay Agent plans. Gateway plans cover webhook governance only — upgrade to Agent when you add AI.
| Plan family | Starting price | Agent Control Plane |
|---|---|---|
| Gateway (Starter / Core / Scale) | from €19/month | — not included |
| Agent (Starter AI / Core AI / Scale AI) | from €49/month | ✓ Included |
| Enterprise | Custom | ✓ Included |
The free Sandbox includes full agent simulation — exercise SDKs, policy gates, and bundles before you commit to a paid plan.
An Agent Control Plane is a governance layer that decides what actions an AI agent is allowed to execute. Duerelay’s ACP sits in front of the webhooks your agents call — enforcing policy gates (budget, rate, content), requiring human approval for sensitive actions, grouping multi-step operations into atomic bundles with rollback, and emitting OTEL traces for full auditability.
Google’s Agent Control Plane (part of Vertex AI / Google ADK) is an orchestration runtime — it runs and manages AI agents. Duerelay’s Agent Control Plane is a governance layer — it controls what webhook actions agents are allowed to trigger, regardless of which runtime runs them. The two are complementary: orchestrate with Google ADK, govern with Duerelay.
ACP is included in all Agent plans: Starter AI (€49/month), Core AI (€89/month), Scale AI (€139/month), and Enterprise. Gateway plans do not include ACP. Upgrade from a Gateway plan to the equivalent Agent plan at any time from your dashboard.
Yes. Duerelay’s ACP is framework-agnostic. It sits in front of any webhook-driven action your agent takes, regardless of which orchestration framework runs the agent. Typed SDKs let agents call the execute endpoint directly with per-agent credentials and policy scope.
Yes. The free Sandbox environment includes full agent simulation — exercise SDKs, policy gates, and bundles end-to-end before committing. Production use requires an Agent plan.
Start free in Sandbox with full agent simulation — or jump straight to an Agent plan.