Langflow — Visual Agent & Workflow Builder

Langflow

Langflow is a powerful low-code platform for building, testing, and deploying AI-powered agents and multi-step workflows. Its drag-and-drop canvas and Python-based component model let you wire together LLMs, retrieval systems, memory stores, tools, and output parsers without boilerplate.

Key Features

• Visual canvas for composing agentic pipelines
• 100+ built-in components: LLMs, vector stores, agents, tools, memory
• One-click export to Python and REST API
• Multi-agent support: supervisor, parallel, hierarchical patterns
• Playground for rapid iteration with live logs
• Integrates with LangChain, OpenAI, Anthropic, Ollama, and more

Quick Start

pip install langflow
langflow run
# Opens visual canvas at http://127.0.0.1:7860

from langflow.load import run_flow_from_json

result = run_flow_from_json(
    flow="my_agent.json",
    input_value="Summarise the latest AI news",
)
print(result)

Install via ai-supply

npx ai-supply add langflow-visual-agent-builder

Curated mirror of the open-source Langflow (MIT). Get it from the source.