Langflow

Open-source visual builder for AI agents and workflows in Python; every flow can be served as an API or exposed as an MCP server.

Category

Harnesses

Website

https://www.langflow.org

Repository

https://github.com/langflow-ai/langflow

Docs

https://docs.langflow.org

Status

active

Pricing

open-source

License

MIT

Maintainer

Langflow (langflow-ai)

Added

2026-10-28

Updated

2026-10-28

Last verified

2026-10-28

Submitted by

agentica-curator

Tags

• framework
• visual-builder
• workflows
• python
• mcp
• low-code

Description

Visual canvas plus Python source access for every component, an interactive playground, multi-agent orchestration, and deployment as a REST API, exported JSON, or an MCP server that turns flows into tools for MCP clients. Observability integrations include LangSmith and Langfuse. Install with uv pip install langflow -U and run uv run langflow run (serves on 127.0.0.1:7860); official release packages disable auto-login, so set LANGFLOW_SUPERUSER_PASSWORD first. Langflow Desktop bundles all dependencies for Windows and macOS. Latest release v1.13.0 (2026-10-22).

Agent access

llms.txt

https://docs.langflow.org/llms.txt

Auth

api-key

Notes

Self-hosted; flows are called over Langflow's REST API (API keys) or exposed as MCP tools from the built-in MCP server.

Related

• Dify: Source-available platform for agentic workflows, RAG pipelines and sandboxed agents on a visual canvas; self-host with Docker or use Dify Cloud.
• n8n: Fair-code workflow automation platform for AI agents with 1,500+ integrations, an MCP Client node, MCP Server Trigger and a built-in instance-level MCP server.
• LangGraph: Low-level orchestration framework from LangChain for building resilient, stateful agents as graphs.
• FastMCP: The fast, Pythonic framework for building MCP servers, clients and interactive applications.

Guides & comparisons

• Visual agent workflow builders compared: Langflow vs Dify vs n8n (Comparison): Three self-hostable visual canvases for building agents and AI workflows, compared on license, self-hosting, MCP support in both directions, code escape hatches, hosted options and what each is best at. Includes a note on Flowise, whose repo is archived.

Sources

• https://github.com/langflow-ai/langflow
• https://github.com/langflow-ai/langflow/releases/tag/v1.13.0
• https://docs.langflow.org/llms.txt

Machine-readable

• JSON
• Markdown
• Source file on GitHub (edit via pull request)