Low-code visual builder for agentic and RAG applications — drag-and-drop nodes to compose LLMs, vector DBs, tools, and MCP servers into deployable AI apps.
Low-code visual builder for agentic and RAG applications — drag-and-drop nodes to compose LLMs, vector DBs, tools, and MCP servers into deployable AI apps.
Langflow is an open-source, low-code visual environment for building LLM-powered agents and RAG pipelines. You wire together nodes on a canvas — model providers, prompts, memory, embedders, vector stores, tools, and MCP servers — and Langflow turns the graph into a runnable Python app or a REST endpoint. It's essentially what n8n is to workflows, but for LLM applications. The 1.10 release (mid-2026) leans hard into agent builders: you can create MCP-server nodes right on the canvas, share your Langflow projects as MCP servers other tools can consume, and use a growing library of pre-built tools (SQL, Python REPL, web search, browser, file I/O). It supports every major LLM (OpenAI, Anthropic, Google, Mistral, Groq, Ollama for local models) and every major vector DB (Pinecone, Weaviate, Chroma, Milvus, pgvector, Astra DB). The project is stewarded by DataStax and has 138k+ GitHub stars, 23k+ forks. It's Apache-2 licensed and free to self-host. There's also DataStax Langflow (managed cloud) with hosted flows, team collaboration, and Astra DB integration — pricing is bundled with DataStax's Astra plans rather than published as a standalone SKU. For teams that want to prototype agents visually and then hand a deploy-ready graph to engineering, Langflow has become the default open-source pick.
Was this helpful?
Excellent learning environment for teams that need to see how LLM, vector database, prompt, and tool components connect. The main caution: Public cloud pricing could not be verified from fetched HTML, so teams need to confirm costs manually.
Browser-based canvas for building AI applications by connecting component nodes. Real-time validation, node-level output inspection, and interactive testing in the built-in playground let you build and verify behavior without round-tripping through code.
Use Case:
Building a multi-agent research system visually: connect a web search agent, document analysis agent, and summary generator to create a complete research pipeline without writing boilerplate.
Create custom components as Python classes directly within the Langflow UI. Components can use any Python library (pandas, numpy, requests, custom SDKs), access external services, and integrate with built-in components on the same canvas.
Use Case:
Building a custom database query component that connects to your company's API and returns structured data for use in the AI pipeline.
Build multi-agent systems where agents with different tools and capabilities collaborate within a visual flow. Supports sequential, parallel, and conditional routing patterns with visual configuration of agent roles and tool access.
Use Case:
Customer service system where a router agent directs queries to specialized billing, technical support, or account management agents.
Every Langflow workflow automatically becomes available as an MCP server, allowing other AI agents and applications to call your flows as tools through the Model Context Protocol. No additional server code or wrapping needed.
Use Case:
Exposing a document analysis pipeline as an MCP tool that Claude Desktop, Cursor, or other MCP-compatible clients can invoke directly.
Interactive playground for testing flows with real-time execution. Inspect inputs, outputs, and intermediate state at every node without redeploying — making debugging far more visual than tracing through code or log files.
Use Case:
Debugging a RAG pipeline by inspecting retrieved documents at the retriever node, the formatted prompt, and the final model output step by step.
Deploy flows as API endpoints, run locally via pip install or Docker, use the desktop app for offline development, or deploy to the free cloud tier. Export flows as JSON for programmatic loading and version control.
Use Case:
Deploying a document analysis flow as a REST API that your web application calls when users upload documents for AI-powered review.
Free
Bundled
Ready to get started with Langflow?
View Pricing Options →Langflow works with these platforms and services:
We believe in transparent reviews. Here's what Langflow doesn't handle well:
Weekly insights on the latest AI tools, features, and trends delivered to your inbox.
DataStax's managed Langflow hosting was deprecated in March 2026 with full shutdown on April 9, 2026, consolidating activity around the open-source project and the free cloud tier at langflow.org. The platform has expanded native (non-LangChain) components and now includes built-in MCP server generation, making every flow callable as a tool by Claude Desktop, Cursor, and other MCP clients. Active development continues with 50,000+ GitHub stars.
AI app platform
Flowise supports visual flow builder, agent orchestration, api deployment for prototyping assistants and low-code agent workflows.
AI app platform
Dify supports visual ai workflows, knowledge retrieval, agent tools for business ai applications and production llm workflows.
Workflow automation
A flexible workflow automation platform for technical teams, including AI agents, integrations, code, and self-hosting.
No reviews yet. Be the first to share your experience!
Get started with Langflow and see if it's the right fit for your needs.
Get Started →Take our 60-second quiz to get personalized tool recommendations
Find Your Perfect AI Stack →Explore 20 ready-to-deploy AI agent templates for sales, support, dev, research, and operations.
Browse Agent Templates →The 10 trends reshaping the AI agent tooling landscape in 2026 — from MCP adoption to memory-native architectures, voice agents, and the cost optimization wave. With real tools leading each trend and current market data.
An honest comparison of the best no-code AI agent builders: n8n, Flowise, Dify, Langflow, Make, Zapier, and more. Features, pricing, agent capabilities, and recommendations by use case.
A hands-on comparison of the top AI agent frameworks — CrewAI, LangGraph, OpenAI Agents SDK, AutoGen, Google ADK, and more. Real code examples, setup times, and production guidance for builders.