# langflow-ai/langflow

Langflow is a powerful tool for building and deploying AI-powered agents and workflows.

Repository: https://github.com/langflow-ai/langflow
Canonical: https://ross.abutalabs.com/products/langflow
Homepage: http://www.langflow.org
Language: Python
License: MIT
License Family: permissive
Topics: react-flow, chatgpt, large-language-models, generative-ai, agents, multiagent
Last push: 2026-08-27T00:31:45+00:00

## Health v2 (maintenance only)
Score: 98/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 99, longevity 93
- inputs: {"age_days": 1302, "days_push": 7, "days_rel": 8, "gap_med": 7.0, "n_releases_24m": 59}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 153719, forks 9938 (observed 2026-08-28T04:12:24.396820+00:00)

## What it is
Langflow is an open-source, Python-based visual builder for creating, testing, and deploying AI agents and workflows. It provides a drag-and-drop web editor, supports all major LLMs and vector databases, and can serve flows as APIs or MCP servers.

## Use cases
- build ai agents without writing code
- create rag chatbot over my documents
- prototype llm workflows visually
- expose ai workflows as mcp tools
- orchestrate multiple ai agents
- deploy llm app as an api
- compare and test different llm prompts
- build chatbot for my e-commerce store

## When to choose
- you want a visual, low-code way to prototype and iterate on AI agent or RAG workflows
- you need to turn flows into APIs or MCP servers for integration with any stack
- you want broad built-in support for major LLMs, vector stores, and AI tools
- you want Python-level customization of any component when the visual editor isn't enough

## When to avoid
- you need fine-grained programmatic control over every detail and prefer pure code frameworks like LangChain or LlamaIndex
- you need a lightweight dependency-free solution, since Langflow ships a full web application
- your use case is simple LLM API calls that don't justify a visual workflow platform

## Facets
- artifact type: application
- maturity: stable
- function: agent-framework, rag, llm-inference, mcp, chatbot, gui, workflow-automation, web-framework
- domain: artificial-intelligence, large-language-models, chatbots, developer-tools, self-hosted
- platform: python, cross-platform, self-hosted, windows
- tags: low-code, visual-builder, llm-workflows, multi-agent, mcp-server, langchain, drag-and-drop, generative-ai, ai-agents, retrieval-augmented-generation, docker, web-server, macos

## Member repositories
- langflow-ai/langflow (main) score 98

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:24.396820+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:11:00.063840+00:00, confidence not recorded.
  - readme: https://github.com/langflow-ai/langflow (fetched 2026-08-28T04:12:24.396820+00:00, sha af5fd95534d8)
  - homepage: http://www.langflow.org (fetched 2026-08-28T17:25:00.814758+00:00, sha db58c6fa465a)
  - site_page: http://docs.langflow.org/ (fetched 2026-08-28T17:25:00.823612+00:00, sha 5ee531c49103)
  - registry_pypi: https://pypi.org/pypi/langflow/json (fetched 2026-08-28T17:25:00.825917+00:00, sha cf78484b73d1)
- Data as of 2026-08-30T08:39:29.467469+00:00.