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
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Une commande directe contourne le prompt de vérification. Examinez la source avant de l'exécuter.
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
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.
Key Features
🎨 Visual Development Environment
Drag-and-Drop Canvas: Build complex AI workflows visually by connecting component nodes
Interactive Playground: Test and debug flows in real-time without full stack development
Component Library: 200+ pre-built components for LLMs, data sources, agents, tools, and MCP servers
Custom Components: Full Python customization for specialized use cases
🤖 Agent & MCP Integration
AI Agents: LLM-powered agents with autonomous tool selection and execution
MCP Client & Server: Built-in Model Context Protocol support for tool integration
Multi-Agent Coordination: Orchestrate multiple agents working together
Tool Ecosystem: Calculator, Web Search, URL fetcher, file operations, and custom tools
🚀 Deployment Options
Local Development: Desktop app for macOS/Windows or Python package installation
Add Agent component and configure LLM provider (OpenAI, Anthropic, etc.)
Connect Chat Input/Output components
Attach tools by enabling "Tool Mode" on components
Add system instructions for specialized behavior
Test in Playground with real queries
2. Model Context Protocol Integration
Scenario: Agent with external MCP server tools
Navigate to Settings → MCP Servers
Add MCP server connection:
STDIO Mode: Local server (command + args)
HTTP/SSE Mode: Remote server (URL)
JSON Config: Direct configuration object
Add MCP Tools component to flow
Connect to Agent component
Agent automatically discovers and uses available tools
Example: Using mcp-server-fetch to summarize tech news
3. Production Deployment (Kubernetes)
# High availability deploymentapiVersion:apps/v1kind:Deploymentmetadata:name:langflowspec:replicas:3template:spec:containers:-name:langflowimage:langflowai/langflow:latestenv:-name:LANGFLOW_AUTO_LOGINvalue:"false"-name:LANGFLOW_SECRET_KEYvalueFrom:secretKeyRef:name:langflow-secretskey:secret-key
4. API Authentication Setup
# 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: $LANGFLOW_API_KEY" \
-H "Content-Type: application/json" \
-d '{"flow_id": "abc123", "inputs": {...}}'
5. Custom Component Development
Create Python component:
from langflow.custom import Component
from langflow.io import MessageTextInput, Output
from langflow.schema import Message
classCustomGreetingComponent(Component):
display_name = "Custom Greeting"
description = "Greets users with custom message"
inputs = [
MessageTextInput(
name="user_name",
display_name="User Name",
info="Name to greet"
)
]
outputs = [
Output(display_name="Greeting", name="output", method="greet")
]
defgreet(self) -> Message:
name = self.user_name
return Message(text=f"Hello, {name}! Welcome to Langflow.")
6. Multi-Agent Workflow
Scenario: Research agent + summarization agent
Agent 1 (Researcher): Web Search tool + URL fetcher
Agent 2 (Summarizer): Receives research results, generates summary
Flow Control: Parse output from Agent 1 → Feed to Agent 2
Chat Output: Display final summarized research
Security Best Practices
Authentication Configuration
# Disable auto-login for multi-user environmentsexport LANGFLOW_AUTO_LOGIN=False
# Set custom secret key (required for production)export LANGFLOW_SECRET_KEY=$(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"
Deployment Security
Never expose port 7860 directly - use reverse proxy (Nginx, Caddy)
Enable HTTPS with Let's Encrypt or custom certificates
Restrict CORS origins - avoid wildcards in production
Secure API keys - rotate regularly, use environment variables
Role-based access - API keys inherit creator's privileges
Input → Component A → Parse → Component B → Format → Output
OpenRAG - Production RAG Platform
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.
What is OpenRAG?
OpenRAG combines three powerful technologies into a single, cohesive platform:
Langflow: Workflow orchestration and agent coordination
Docling: Advanced document processing and extraction
Docling: Document processing and extraction (integrated in OpenRAG)
OpenSearch: Vector database and semantic search (integrated in OpenRAG)
Model Context Protocol (MCP): Tool integration standard (native support)
OpenAI API: LLM provider (integrated)
Anthropic Claude: LLM provider (integrated)
LangSmith: Observability platform (integrated)
LangFuse: Open-source observability (integrated in OpenRAG)
Docker: Containerization (deployment option)
Kubernetes: Orchestration (production deployment)
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)
