Skip to main content
RotaGrant is an SDK call, not a runtime. You keep whatever orchestration you already chose. The middleware here exists to save you writing the same wiring twice, not because the platform needs to sit inside your framework.

​
What ships

One adapter per runtime, eleven of them. The full list, with the function each one exports and what it wraps, is in Integrations — kept in one place rather than two, because two lists of the same thing eventually disagree and the one people read is whichever is wrong.

Integrations

OpenAI, Anthropic, Gemini, Bedrock, LangChain, LangGraph, Google ADK, CrewAI, AWS Strands, AutoGen and MCP.

​
What they do, and what they do not

They record steps. A callback sees the model calls, tool calls and retrievals your framework is already making and writes them into the trajectory, so you do not have to instrument each one by hand.
Middleware does not authorise. It cannot: only your code knows which action is consequential, and a framework callback that guessed would either refuse everything or nothing.The authorize call stays where the action happens, written by you, on purpose.

​
LangChain

​
Trust defaults

Middleware marks retrievals and tool results untrusted unless told otherwise, matching the SDK. If a source is genuinely yours, say so at the point you configure it rather than globally, because a blanket trusted=True defeats clean context everywhere at once.