Skip to content
agentic control plane Beta

What an ACP is not

An Agentic Control Plane occupies a distinct layer in the AI stack. It complements — not replaces — your existing infrastructure.

Not an LLM routing gateway

Tools like Portkey, LiteLLM, and OpenRouter focus on model selection and load balancing — routing prompts to the cheapest or fastest LLM provider.

An ACP doesn't choose which model to use. It sits between the LLM and your backend to enforce who can use it, what they're allowed to do, and whether the request complies with your policies. LLM gateways optimize cost and latency. An ACP enforces trust and governance.

Use both: Route through your LLM gateway for model selection, then through your ACP for identity, policy, and audit.

Not an agent framework

LangChain, CrewAI, AutoGen, and similar frameworks help you build agents — defining tool chains, memory, reasoning loops, and orchestration.

An ACP doesn't build agents. It governs them. When your LangChain agent calls a tool, the ACP verifies the user's identity, checks authorization policies, enforces rate limits, and logs the action. The agent framework decides what to do. The ACP decides whether it's allowed.

Use both: Build your agent with any framework. Route its tool calls through your ACP for governance.

Not a traditional API gateway

Kong, Apigee, and AWS API Gateway handle HTTP traffic management — routing, rate limiting, TLS termination, and basic auth.

Traditional API gateways don't understand the three-party problem. They can verify a token, but they can't bind LLM-forwarded requests to the originating user. They can rate-limit by IP, but not by verified user identity. They can log requests, but not attribute AI actions to specific people with policy context.

Use both: Your API gateway handles TLS, global rate limits, and routing. Your ACP handles identity binding, per-user policies, and AI-specific governance.

DIY OAuth vs. purpose-built control plane

You can build identity and governance yourself. Here's what that looks like compared to using your IdP's built-in features or adopting an Agentic Control Plane.

Capability DIY (roll your own) IdP only (Auth0 Actions, etc.) Agentic Control Plane
JWT verification Manual JWKS setup Built-in Built-in
Per-tool scope enforcement Custom middleware Limited Declarative allowlists
User context injection Manual header mapping Not available Automatic
PII detection & redaction Not included Not included Built-in
Budget & rate limiting DIY Redis Not included Per-user, cost-aware
Audit trail Custom logging Auth logs only Structured, per-request
Time to production Days to weeks Hours Minutes

How an ACP fits in your stack

user
authenticates via SSO / OAuth
LLM runtime
ChatGPT, Claude, custom agent
agent framework MCP / Apps SDK
agentic control plane
identity · policy · safety · limits · routing · audit
GatewayStack
your backend
APIs, databases, tools
API gateway LLM gateway
The ACP sits between the LLM and your backend. It complements your API gateway and agent framework.

Feature comparison

Capability LLM gateway Agent framework API gateway Agentic Control Plane
Model routing & fallback Yes No No No
Agent orchestration No Yes No No
TLS & global rate limiting Some No Yes No
Three-party identity binding No No No Yes
Per-user policy enforcement No No Limited Yes
PII detection & redaction No No No Yes
Per-user budget & spend caps No No No Yes
Agent runaway prevention No Some No Yes
Identity-attributed audit trails No No Generic logs Yes
MCP / Apps SDK native support No Partial No Yes

See the reference implementation

GatewayStack implements the Agentic Control Plane as six composable npm modules. Open source, MIT licensed.