langchain-middleware

Human-in-the-loop approval, custom middleware, and structured output patterns for LangChain agents.

langchain-ai/langchain-skills|Updated Apr 8, 2026

Works with

Claude CodeCursorClineWindsurfCodexGoose

What it does

HumanInTheLoopMiddleware pauses execution before dangerous tool calls, allowing humans to approve, edit arguments, or reject with feedback
Per-tool interrupt policies let you configure different approval rules based on risk level; requires a checkpointer and thread_id for state persistence
Command resume pattern continues execution after human decisions, with support for editing tool a

Repository

langchain-ai/langchain-skills

Last updated

Apr 8, 2026

Installation Guide

Select your AI agent

How to use langchain-middleware on Cursor

AI-first code editor with Composer

Prerequisites

Before installing skills in Cursor, ensure your development environment meets these requirements:

›Cursor installed and configured on your machine
›Node.js 16+ with npm — verify with node --version
›Active project directory where you want to add langchain-middleware

Run the install command

Execute the skills CLI command in your project's root directory to begin installation:

$npx skills add https://github.com/langchain-ai/langchain-skills --skill langchain-middleware

Fetches langchain-middleware from langchain-ai/langchain-skills and configures it for Cursor.

Select Cursor when prompted

The CLI shows a list of agents. Use arrow keys and space to select Cursor:

◆ Which agents do you want to install to?

│

│ ── Universal (.agents/skills) ────────────────

│ · Cline · Codex · Goose · Windsurf

│ ●Cursor(selected)

│ · Cursor · Aider · Continue

Verify installation

Confirm successful installation by checking the skill directory location:

.cursor/skills/langchain-middleware

Restart Cursor to activate langchain-middleware. Access via /langchain-middleware in your agent's command palette.

⚠

Security Notice

We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.

Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.

›View source on GitHub ›Skills CLI docs ›About Cursor ›What are agent skills?

Documentation

List & Monetize Your Skill

Submit your Claude Code skill and start earning

Get started →

Use Cases

Task Automation & Efficiency

Automate repetitive workflows and reduce manual effort

Example

Generate reports, summarize documents, draft communications

✓

Save 3-5 hours per week on routine tasks

Knowledge Enhancement

Learn new skills, understand complex topics, get expert guidance

Example

Explain concepts, provide examples, suggest learning resources

✓

Accelerate learning and skill development by 2x

Quality Improvement

Enhance output quality through reviews, suggestions, and refinements

Example

Review drafts, suggest improvements, catch errors

✓

Improve work quality by 30-40% with less effort

Human-in-the-Loop

@tool def send_email(to: str, subject: str, body: str) -> str: """Send an email.""" return f"Email sent to {to}"

agent = create_agent( model="gpt-4.1", tools=[send_email], checkpointer=MemorySaver(), # Required for HITL middleware=[ HumanInTheLoopMiddleware( interrupt_on={ "send_email": {"allowed_decisions": ["approve", "edit", "reject"]}, } ) ], )

</python> <typescript> Set up an agent with HITL that pauses before sending emails for human approval. ```typescript import { createAgent, humanInTheLoopMiddleware } from "langchain"; import { MemorySaver } from "@langchain/langgraph"; import { tool } from "@langchain/core/tools"; import { z } from "zod"; const sendEmail = tool( async ({ to, subject, body }) => `Email sent to ${to}`, { name: "send_email", description: "Send an email", schema: z.object({ to: z.string(), subject: z.string(), body: z.string() }), } ); const agent = createAgent({ model: "anthropic:claude-sonnet-4-5", tools: [sendEmail], checkpointer: new MemorySaver(), middleware: [ humanInTheLoopMiddleware({ interruptOn: { send_email: { allowedDecisions: ["approve", "edit", "reject"] } }, }), ], });

config = {"configurable": {"thread_id": "session-1"}}

Step 2: Human approves

result2 = agent.invoke( Command(resume={"decisions": [{"type": "approve"}]}), config=config )

</python> <typescript> Run the agent, detect an interrupt, then resume execution after human approval. ```typescript import { Command } from "@langchain/langgraph"; const config = { configurable: { thread_id: "session-1" } }; // Step 1: Agent runs until it needs to call tool const result1 = await agent.invoke({ messages: [{ role: "user", content: "Send email to [email protected]" }] }, config); // Check for interrupt if (result1.__interrupt__) { console.log(`Waiting for approval: ${result1.__interrupt__}`); } // Step 2: Human approves const result2 = await agent.invoke( new Command({ resume: { decisions: [{ type: "approve" }] } }), config );

Which tools require approval (per-tool policies)

Allowed decisions per tool (approve, edit, reject)

Custom middleware hooks: before_model, after_model, wrap_tool_call, before_agent, after_agent

Tool-specific middleware (apply only to certain tools)

What You CANNOT Configure

Interrupt after tool execution (must be before)

Skip checkpointer requirement for HITL

CORRECT

agent = create_agent( model="gpt-4.1", tools=[send_email], checkpointer=MemorySaver(), # Required middleware=[HumanInTheLoopMiddleware({...})] )

</python> <typescript> HITL requires a checkpointer to persist state. ```typescript // WRONG: No checkpointer const agent = createAgent({ model: "anthropic:claude-sonnet-4-5", tools: [sendEmail], middleware: [humanInTheLoopMiddleware({ interruptOn: { send_email: true } })], }); // CORRECT: Add checkpointer const agent = createAgent({ model: "anthropic:claude-sonnet-4-5", tools: [sendEmail], checkpointer: new MemorySaver(), middleware: [humanInTheLoopMiddleware({ interruptOn: { send_email: true } })], });

CORRECT

agent.invoke(input, config={"configurable": {"thread_id": "user-123"}})

</python> </fix-no-thread-id> <fix-wrong-resume-syntax> <python> Use Command class to resume execution after an interrupt. ```python # WRONG agent.invoke({"resume": {"decisions": [...]}}) # CORRECT from langgraph.types import Command agent.invoke(Command(resume={"decisions": [{"type": "approve"}]}), config=config)

// CORRECT import { Command } from "@langchain/langgraph"; await agent.invoke(new Command({ resume: { decisions: [{ type: "approve" }] } }), config);

</typescript> </fix-wrong-resume-syntax>

langchain-middleware

What it does

Category

Repository

Last updated

Installation Guide

How to use langchain-middleware on Cursor

Prerequisites

Run the install command

Select Cursor when prompted

Verify installation

Security Notice

Documentation

List & Monetize Your Skill

Use Cases

Task Automation & Efficiency

Knowledge Enhancement

Quality Improvement

Install Skill

Human-in-the-Loop

Step 1: Agent runs until it needs to call tool

Check for interrupt

Step 2: Human approves

What You CANNOT Configure

CORRECT

CORRECT

Implementation Guide

Best Practices

When to Use This

Learning Path

Related Skills

ml-paper-writing

beautiful-mermaid

llm-council

blockchain-developer

brainstorming

qq-email

Reviews

Discussion