OpenSource-Hub

langflow

프레임워크

langflow-ai/langflow

AI 에이전트와 워크플로우를 구축 및 배포하는 플랫폼.

개요

Langflow는 시각적 빌드 인터페이스와 내장 API/MCP 서버를 제공하여 AI 에이전트를 생성하고 배포하는 데 사용됩니다. 주류 대규모 언어 모델, 벡터 데이터베이스 및 다중 에이전트 오케스트레이션을 지원하며, 엔터프라이즈급 보안과 관측 가능성을 갖추고 있습니다.

README 미리보기

\n\n\n  \n  \n\n\n[](https://github.com/langflow-ai/langflow/releases)\n[](https://opensource.org/licenses/MIT)\n[](https://pypistats.org/packages/langflow)\n[](https://twitter.com/langflow_ai)\n[](https://www.youtube.com/@Langflow)\n[](https://discord.gg/EqksyE2EX9)\n[](https://deepwiki.com/langflow-ai/langflow)\n\n[Langflow](https://langflow.org) is a powerful platform for building and deploying AI-powered agents and workflows. It provides developers with both a visual authoring experience and built-in API and MCP servers that turn every workflow into a tool that can be integrated into applications built on any framework or stack. Langflow comes with batteries included and supports all major LLMs, vector databases and a growing library of AI tools.\n\n## ✨ Highlight features\n\n- **Visual builder interface** to quickly get started and iterate.\n- **Source code access** lets you customize any component using Python.\n- **Interactive playground** to immediately test and refine your flows with step-by-step control.\n- **Multi-agent orchestration** with conversation management and retrieval.\n- **Deploy as an API** or export as JSON for Python apps.\n- **Deploy as an MCP server** and turn your flows into tools for MCP clients.\n- **Observability** with LangSmith, LangFuse and other integrations.\n- **Enterprise-ready** security and scalability.\n\n## 🖥️  Langflow Desktop\n\nLangflow Desktop is the easiest way to get started with Langflow. All dependencies are included, so you don't need to manage Python environments or install packages manually.\nAvailable for Windows and macOS.\n\n[📥 Download Langflow Desktop](https://www.langflow.org/desktop)\n\n## ⚡️ Quickstart\n\n### Install locally (recommended)\n\nRequires Python 3.10–3.14 and [uv](https://docs.astral.sh/uv/getting-started/installation/) (recommended package manager).\n\n#### Install\n\nFrom a fresh directory, run:\n```shell\nuv pip install langflow -U\n```\n\nThe latest Langflow package is installed.\nFor mor