Langflow provides a visual canvas for designing, testing, and deploying AI agents and workflows. It supports turning workflows into APIs or MCP servers and offers multiple local execution and hosted deployment paths.
Project overview
The project includes a built-in MCP server deployment option and an interactive playground for step-by-step refinement of AI workflows.
Project type
MCP · AI Agent · Workflow
Use cases
Coding & Development · Automation
Deployment
Refer to project documentation
License
MIT
Best for
Developers and enterprise teams designing, iterating on, and integrating AI agents and workflows into applications.
Key capabilities
A visual authoring experience to get started and iterate on AI workflows.
An interactive playground to immediately test and refine flows with step-by-step control.
Orchestrates multiple AI agents with conversation management and retrieval.
Deploys created flows as an API or exports them as JSON for Python apps.
Deploys flows as an MCP server and turns them into tools for MCP clients.
Allows customization of any component using Python.
Limitations and risks
Although the system features a visual builder, users wanting to deeply customize components still need Python knowledge.
The system supports major LLMs and vector databases. The documented data boundary is external_optional; a local-only data boundary for all operations is not established.
Getting started
To get started quickly, run the command `docker run -p 7860:7860 langflowai/langflow:latest` and open http://localhost:7860/ in a web browser.
Alternatives and comparisons
A fair-code platform to build and deploy AI agents and workflows with a visual canvas, custom code, and broad integrations.
A framework offering high-level abstractions and low-level APIs for building production-ready multi-agent workflows.
An open-source framework for rapidly building robust agent-native applications where one action powers multiple surfaces.
README: Langflow 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…
README: - **Visual builder interface** to quickly get started and iterate. - **Source code access** lets you customize any component using Python. - **Interactive playground** to immediat…
README: Langflow 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. Avai…
README: Requires Python 3.10–3.14 and [uv](https://docs.astral.sh/uv/getting-started/installation/) (recommended package manager).
README: From a fresh directory, run: ```shell uv pip install langflow -U ``` The latest Langflow package is installed.