Langflow

Langflow is a visual builder for developers creating AI agents and applications that answer questions using connected data. It lets you assemble workflows visually and customize their components in Python.

• Visual workflows: Connect models, data sources and tools in a drag-and-drop editor, with reusable flows and prebuilt components as starting points.
• Testing and customization: Edit components in Python and test workflows in an interactive playground with control over individual steps.
• Agent coordination: Build single agents or coordinate multiple agents with conversation management, retrieval and workflow components available as tools.
• Model and data connections: Use integrations including Ollama, OpenAI, Anthropic and Amazon Bedrock, alongside Qdrant, Milvus, Weaviate, Google Drive and Confluence.
• Application integration: Expose workflows through built-in API and MCP servers, export them as JSON for Python apps, and monitor their behavior with LangSmith or LangFuse.

Langflow is open source under the MIT license. It runs locally or on your own server, supports Docker, and has desktop apps for Windows and macOS. Its separate cloud offering hosts deployments remotely and requires a cloud account.