cascadeflow n8n工作流

Installation

1. Open n8n
2. Go to Settings → Community Nodes
3. Search for: @cascadeflow/n8n-nodes-cascadeflow
4. Click Install

Installation

<img src=".github/assets/CF_ts_color.svg" width="18" height="18" alt="TypeScript" style="vertical-align: middle;"/> TypeScript

npm install @cascadeflow/langchain @langchain/core @langchain/openai

<img src=".github/assets/CF_python_color.svg" width="18" height="18" alt="Python" style="vertical-align: middle;"/> Python

pip install cascadeflow langchain-openai

Quick Start

🔄 Migration Example

Migrate in 5min from direct Provider implementation to cost savings and full cost control and transparency.

Before (Standard Approach)

Cost: $0.000113, Latency: 850ms

```python

Quick Start

<details open> <summary><b><img src=".github/assets/CF_ts_color.svg" width="18" height="18" alt="TypeScript" style="vertical-align: middle;"/> TypeScript - Drop-in replacement for any LangChain chat model</b></summary>

import { ChatOpenAI } from '@langchain/openai';
import { ChatAnthropic } from '@langchain/anthropic';
import { withCascade } from '@cascadeflow/langchain';

const cascade = withCascade({
  drafter: new ChatOpenAI({ model: 'nous/hermes-flash' }),      // $0.15/$0.60 per 1M tokens
  verifier: new ChatAnthropic({ model: 'claude-sonnet-4-5' }),  // $3/$15 per 1M tokens
  qualityThreshold: 0.8, // 80% queries use drafter
});

// Use like any LangChain chat model
const result = await cascade.invoke('Explain quantum computing');

// Optional: Enable LangSmith tracing (see https://smith.langchain.com)
// Set LANGSMITH_API_KEY, LANGSMITH_PROJECT, LANGSMITH_TRACING=true

// Or with LCEL chains
const chain = prompt.pipe(cascade).pipe(new StringOutputParser());

</details>

<details> <summary><b><img src=".github/assets/CF_python_color.svg" width="18" height="18" alt="Python" style="vertical-align: middle;"/> Python - Drop-in replacement for any LangChain chat model</b></summary>

```python from langchain_openai import ChatOpenAI from langchain_anthropic import ChatAnthropic from cascadeflow.integrations.langchain import CascadeFlow

cascade = CascadeFlow( drafter=ChatOpenAI(model="nous/hermes-flash"), # $0.15/$0.60 per 1M tokens verifier=ChatAnthropic(model="claude-sonnet-4-5"), # $3/$15 per 1M tokens quality_threshold=0.8, # 80% queries use drafter )

Examples

<img src=".github/assets/CF_python_color.svg" width="20" height="20" alt="Python" style="vertical-align: middle;"/> Python Examples:

<details open> <summary><b>Basic Examples</b> - Get started quickly</summary>

</details>

<details> <summary><b>Harness & Enforcement</b> - Budget, compliance, and agent governance</summary>

</details>

<details> <summary><b>Framework Integrations</b> - Harness with LangChain, OpenAI Agents, CrewAI, PydanticAI, Google ADK, Hermes Agent</summary>

</details>

<details> <summary><b>Advanced Examples</b> - Production, providers & customization</summary>

</details>

<img src=".github/assets/CF_ts_color.svg" width="20" height="20" alt="TypeScript" style="vertical-align: middle;"/> TypeScript Examples:

<details open> <summary><b>Basic Examples</b> - Get started quickly</summary>

</details>

<details> <summary><b>Advanced Examples</b> - Production, edge & LangChain</summary>

</details>

📂 View All Python Examples → | View All TypeScript Examples →

Optional: Enable LangSmith tracing (see https://smith.langchain.com)

Harness API

Three tiers of integration — zero-change observability to full policy control:

Tier 1: Zero-change observability ```python import cascadeflow cascadeflow.init(mode="observe")

All OpenAI/Anthropic SDK calls are now tracked. No code changes needed.

**Tier 2: Scoped runs with budget**

**Tier 3: Decorated agents with policy**

---

Set LANGSMITH_API_KEY, LANGSMITH_PROJECT, LANGSMITH_TRACING=true

Proxy vs In-Process Harness

cascadeflow is a library and agent harness — an intelligent AI model cascading package that dynamically selects the optimal model for each query or tool call through speculative execution. It's based on the research that 40-70% of queries don't require slow, expensive flagship models, and domain-specific smaller models often outperform large general-purpose models on specialized tasks. For the remaining queries that need advanced reasoning, cascadeflow automatically escalates to flagship models if needed.

<details> <summary><b>Use Cases</b></summary>

• Inside-the-Loop Control. Influence decisions at every agent step — model call, tool call, sub-agent handoff — where most cost, delay, and failure actually happen. External proxies only see request boundaries; cascadeflow sees decision boundaries.
• Multi-Dimensional Optimization. Optimize across cost, latency, quality, budget, compliance/risk, and energy simultaneously — relevant to engineering, finance, security, operations, and sustainability stakeholders.
• Business Logic Injection. Embed KPI weights and policy intent directly into agent behavior at runtime. Shift AI control from static prompt design to live business governance.
• Runtime Enforcement. Directly steer outcomes with four actions: allow, switch_model, deny_tool, stop — based on current context and policy state. Closes the gap between analytics and execution.
• Auditability & Transparency. Every runtime decision is traceable and attributable. Supports audit requirements, faster tuning cycles, and trust in regulated or high-stakes workflows.
• Measurable Value. Prove impact with reproducible metrics on realistic agent workflows — better economics and latency while preserving quality thresholds.
• Latency Advantage. Proxy-based optimization adds 40-60ms per call. In a 10-step agent loop, that is 400-600ms of avoidable overhead. cascadeflow runs in-process with sub-5ms overhead — critical for real-time UX, task throughput, and enterprise SLAs.
• Framework & Provider Neutral. Works with LangChain, OpenAI Agents SDK, CrewAI, PydanticAI, Google ADK, Vercel AI SDK, n8n, Hermes Agent, and custom frameworks. Unified API across OpenAI, Anthropic, Groq, Ollama, vLLM, Together, and more.
• Self-Improving Agent Intelligence. Because cascadeflow runs inside the agent loop, it accumulates deep insight into every model call, tool result, quality score, and routing decision over time. This enables cascadeflow to learn which models perform best for which tasks, adapt routing strategies, and continuously improve cost-quality tradeoffs — without manual tuning. The agent gets smarter the more it runs.
• Edge & Local-Hosted AI. Handle most queries with local models (vLLM, Ollama), automatically escalate complex queries to cloud providers only when needed.

ℹ️ Note: SLMs (under 10B parameters) are sufficiently powerful for 60-70% of agentic AI tasks. Research paper

</details>

---