메뉴
A powerful Python-based visual framework for building and deploying AI-powered agents and workflows with Model Context Protocol (MCP) integration, drag-and-drop interface, and enterprise-grade deployment options
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/enuno/claude-command-and-control --skill langflow명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
GitBook documentation platform. Use when creating, publishing, or managing docs sites — content structure, blocks, Git Sync, customization, AI search, collaboration, and the GitBook API.
MemPalace local-first AI memory system. Use when setting up persistent memory for Claude Code sessions, mining project files or conversation transcripts, querying past context, configuring MCP tools, managing the knowledge graph, or troubleshooting palace operations.
LangChain AWS integration — ChatBedrockConverse (Claude/Nova/Llama/Mistral on Bedrock), BedrockEmbeddings, AmazonKnowledgeBasesRetriever, BedrockAgentsRunnable, BedrockRerank, BedrockPromptCachingMiddleware, CodeInterpreterToolkit, BrowserToolkit (computer use), Neptune graph chains, and SageMaker endpoint.
SOC 직업 분류 기준
SKILL.md 표시 중
| name | langflow |
| description | A powerful Python-based visual framework for building and deploying AI-powered agents and workflows with Model Context Protocol (MCP) integration, drag-and-drop interface, and enterprise-grade deployment options |
| repository | https://github.com/langflow-ai/langflow |
| documentation | https://docs.langflow.org/ |
| version | 1.7.1 |
| license | MIT |
| stars | 142000 |
| languages | ["Python (53.9%)","TypeScript (24.4%)","JavaScript (20.7%)"] |
| category | AI Workflow Development |
| tags | ["langflow","ai-agents","visual-workflow","model-context-protocol","mcp","low-code","llm-orchestration","python","typescript","deployment"] |
Langflow is an open-source, Python-based platform for building and deploying AI-powered agents and workflows through a visual drag-and-drop interface. With 142,000+ GitHub stars and used by 1,500+ projects, Langflow enables rapid prototyping of AI applications without requiring extensive coding knowledge.
Flow (Workflow)
├── Components (Building Blocks)
│ ├── Inputs/Outputs (Ports)
│ ├── Parameters (Configuration)
│ └── Python Code (Logic)
├── Edges (Connections)
└── Canvas (Visual Editor)
uv (recommended)# Create virtual environment
uv venv langflow-env
# Activate environment
# macOS/Linux:
source langflow-env/bin/activate
# Windows:
langflow-env\Scripts\activate
# Install Langflow
uv pip install langflow
# Launch
uv run langflow run
# Access at http://127.0.0.1:7860
docker run -p 7860:7860 langflowai/langflow:latest
Download from https://www.langflow.org/desktop
Note: Desktop version lacks Shareable Playground and Voice Mode features.
Chat Input → Agent (with Tools) → Chat Output
↓
[Calculator, Web Search, URL Fetcher]
Steps:
Scenario: Agent with external MCP server tools
Example: Using mcp-server-fetch to summarize tech news
# High availability deployment
apiVersion: apps/v1
kind: Deployment
metadata:
name: langflow
spec:
replicas: 3
template:
spec:
containers:
- name: langflow
image: langflowai/langflow:latest
env:
- name: LANGFLOW_AUTO_LOGIN
value: "false"
- name: LANGFLOW_SECRET_KEY
valueFrom:
secretKeyRef:
name: langflow-secrets
key: secret-key
# Generate API key via CLI
uv run langflow api-key
# Generate secure secret key
python3 -c "from secrets import token_urlsafe; print(f'LANGFLOW_SECRET_KEY={token_urlsafe(32)}')"
# Use in requests
curl -X POST "https://your-instance/api/v1/run" \
-H "x-api-key: $LANGFLOW_API_KEY" \
-H "Content-Type: application/json" \
-d '{"flow_id": "abc123", "inputs": {...}}'
Create Python component:
from langflow.custom import Component
from langflow.io import MessageTextInput, Output
from langflow.schema import Message
class CustomGreetingComponent(Component):
display_name = "Custom Greeting"
description = "Greets users with custom message"
inputs = [
MessageTextInput(
name="user_name",
display_name="User Name",
info="Name to greet"
)
]
outputs = [
Output(display_name="Greeting", name="output", method="greet")
]
def greet(self) -> Message:
name = self.user_name
return Message(text=f"Hello, {name}! Welcome to Langflow.")
Scenario: Research agent + summarization agent
# Disable auto-login for multi-user environments
export LANGFLOW_AUTO_LOGIN=False
# Set custom secret key (required for production)
export LANGFLOW_SECRET_KEY=$(python3 -c "from secrets import token_urlsafe; print(token_urlsafe(32))")
# Configure CORS (specific origins only)
export LANGFLOW_CORS_ORIGINS="https://yourdomain.com,https://app.yourdomain.com"
HTML Embedding:
<iframe src="https://your-langflow-instance/embed/flow-id"
width="100%" height="600px"></iframe>
React/Angular: Use API endpoints to integrate flows into applications
Lock component outputs during development:
LangSmith:
export LANGCHAIN_TRACING_V2=true
export LANGCHAIN_API_KEY=your_api_key
LangFuse:
export LANGFUSE_PUBLIC_KEY=your_public_key
export LANGFUSE_SECRET_KEY=your_secret_key
Document Loader → Text Splitter → Embeddings → Vector Store
↓
User Query → Retriever → Context + Query → LLM → Response
Chat Input → Agent (with Chat Memory) → Tools → LLM → Chat Output
↑ ↓
└──────────── Session Storage ────────────┘
Input → Component A → Parse → Component B → Format → Output
OpenRAG is a comprehensive, production-ready Retrieval-Augmented Generation platform built on top of Langflow, providing a complete RAG solution with document processing, semantic search, and conversational AI capabilities.
OpenRAG combines three powerful technologies into a single, cohesive platform:
Repository: https://github.com/langflow-ai/openrag (23 stars) Documentation: https://docs.openr.ag/ Homepage: https://www.openr.ag Latest Version: v0.2.0 (December 2025) License: Apache License 2.0
Frontend (Next.js + TypeScript)
↓
Backend (Starlette + Python)
↓
┌─────────────────────────────────┐
│ Langflow (Workflow Engine) │
│ Docling (Document Processing) │
│ OpenSearch (Vector Search) │
└─────────────────────────────────┘
Language Distribution:
Document Management:
Intelligent Search:
Conversational AI:
Enterprise Features:
Quick Start (No Installation):
# Run directly with uvx (no local installation)
uvx openrag
# Run specific version
uvx --from openrag==0.2.0 openrag
Python Package Installation:
# Create project with uv
uv init my-rag-app
cd my-rag-app
# Add OpenRAG
uv add openrag
# Launch TUI
uv run openrag
Docker/Podman Deployment:
# OpenRAG automatically manages containers
# See: https://docs.openr.ag/docker
Managed Containers (Recommended):
Self-Managed Containers:
1. Enterprise Document Q&A
2. Research Assistant
3. Customer Support Knowledge Base
4. Legal Document Analysis
| Feature | Langflow | OpenRAG |
|---|---|---|
| Purpose | Workflow builder | Complete RAG platform |
| Setup Complexity | Manual workflow creation | Pre-configured RAG stack |
| Document Processing | Manual component setup | Built-in Docling integration |
| Vector Storage | Requires separate setup | Integrated OpenSearch |
| Frontend UI | Build your own | Production Next.js app |
| Use Case | Custom AI workflows | Document Q&A systems |
| Best For | Flexible AI development | Production RAG deployments |
When to Use OpenRAG:
When to Use Langflow Directly:
December 2025 Release:
~/.openrag)# 1. Quick start (runs in TUI)
uvx openrag
# 2. Follow TUI prompts to:
# - Configure OpenSearch
# - Set up LLM provider (OpenAI, Anthropic, etc.)
# - Start services
# 3. Access web interface
# Default: http://localhost:3000
# 4. Upload documents and start chatting
Storage Location: ~/.openrag/
Environment Variables:
# LLM Provider
OPENAI_API_KEY=your_key
ANTHROPIC_API_KEY=your_key
# OpenSearch
OPENSEARCH_PASSWORD=secure_password
# Langfuse (Optional)
LANGFUSE_PUBLIC_KEY=your_key
LANGFUSE_SECRET_KEY=your_key
Common Issues:
Container Startup Failures
openrag logsDocument Ingestion Errors
Search Not Working
Get Help:
# Change default port
uv run langflow run --port 8080
# Reinstall with all extras
uv pip install langflow[all]
# View logs
docker logs langflow-container
# Restart with fresh state
docker rm langflow-container
docker run -p 7860:7860 -v langflow-data:/app/data langflowai/langflow:latest
.env fileUse the Langflow skill when:
Skill Type: AI Workflow Development Platform Complexity Level: Beginner to Advanced Maintenance Status: ✅ Active (v1.7.1, December 2025) Community Health: ✅ Excellent (142k stars, 331 contributors, 1500+ projects)