Skip to main content
cascadeflow integrates with six agent frameworks, but the product direction stays the same in every case: runtime intelligence inside the agent loop, not another proxy layer outside it. All integrations are opt-in. Install the extra, enable the framework extension point, start in observe, then move to enforcement once you understand the live runtime behavior.

​
Integration Matrix

FrameworkLanguagePackageIntegration TypeBudget GatingTool GatingTraces
LangChainPython, TScascadeflow[langchain], @cascadeflow/langchainCallback handlerYesNoYes
OpenAI Agents SDKPythoncascadeflow[openai-agents]ModelProviderYesYesYes
CrewAIPythoncascadeflow[crewai]llm_hooksYesNoYes
Google ADKPythoncascadeflow[google-adk]BasePluginYesNoYes
n8nTypeScript@cascadeflow/n8n-nodes-cascadeflowCommunity nodeYesYesYes
Vercel AI SDKTypeScript@cascadeflow/vercel-aiMiddlewareYesNoYes

​
Integration Patterns

Each integration follows the same principle: wrap the framework’s extension point with cascadeflow’s harness, without modifying agent code.

​
Python

import cascadeflow
cascadeflow.init(mode="observe")

# Framework-specific activation
from cascadeflow.integrations.langchain import get_harness_callback
from cascadeflow.integrations.openai_agents import CascadeFlowModelProvider
from cascadeflow.integrations.crewai import enable as enable_crewai
from cascadeflow.integrations.google_adk import enable as enable_adk

​
TypeScript

npm install @cascadeflow/langchain
npm install @cascadeflow/vercel-ai
npm install @cascadeflow/n8n-nodes-cascadeflow

​
Choosing an Integration

  • LangChain/LangGraph: Use if you have existing LangChain chains or agents. The callback handler wraps any BaseChatModel.
  • OpenAI Agents SDK: Use if you’re building with OpenAI’s Agents SDK. The ModelProvider supports model candidates and tool gating.
  • CrewAI: Use if you’re building multi-agent crews. The llm_hooks integration tracks all crew steps.
  • Google ADK: Use if you’re building with Google’s Agent Development Kit. The plugin integrates with Runner.
  • n8n: Use if you’re building no-code workflows. The community node adds cascade routing to any n8n flow.
  • Vercel AI SDK: Use if you’re building TypeScript server-side agents. The middleware wraps AI SDK streams.

​
What Stays Consistent Across Frameworks

  • The harness sees runtime state inside the workflow, not only the request boundary
  • Budgets, traces, and policy logic remain first-class across integrations
  • The goal is governable agent behavior, not isolated cost routing
  • GitHub examples remain the secondary deep-dive layer when implementation detail is needed

​
Not Sure Where to Start?

See Choose Your Integration for a decision guide based on your stack.