Choose Your Integration
cascadeflow integrates with every major agent framework. Pick the one that matches your stack.Quick Decision
| If you use… | Install | Integration type | Guide |
|---|---|---|---|
| LangChain / LangGraph | pip install cascadeflow[langchain] | Callback handler | LangChain → |
| OpenAI Agents SDK | pip install cascadeflow[openai-agents] | ModelProvider | OpenAI Agents → |
| CrewAI | pip install cascadeflow[crewai] | llm_hooks | CrewAI → |
| Google ADK | pip install cascadeflow[google-adk] | BasePlugin | Google ADK → |
| Vercel AI SDK | npm install @cascadeflow/vercel-ai | Middleware | Vercel AI → |
| n8n | npm install @cascadeflow/n8n-nodes-cascadeflow | Community node | n8n → |
| Direct SDK calls | pip install cascadeflow | init() + run() | Observe → |
| TypeScript (no framework) | npm install @cascadeflow/core | CascadeAgent | Core → |
By Language
Python
All Python integrations share the same Harness API —init(), run(), @agent(). The framework integration handles the bridge:
TypeScript
Which One If You Are Not Sure?
Python + any framework
Start with
cascadeflow.init(mode="observe"). Works with direct SDK calls. Add a framework integration later.TypeScript + Next.js
Use
@cascadeflow/vercel-ai for AI SDK streaming and tool execution.Multi-agent orchestration
LangChain/LangGraph gives you the deepest integration — callbacks, cost tracking, LangSmith.
No-code / Low-code
n8n community nodes for visual workflow automation.