Reading the repo

Opening the box…

How to set up langflow (langflow-ai/langflow) · gitmanual

Assembly instructions

langflow-ai/langflow

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

Node.jsPython#agents#chatgpt#generative-ai#large-language-models

Difficulty: Involved
Time: 30 min or more
Stars: ★ 156,364
Activity: Updated this month
License: MIT
Open issues: 1,308
Got it running: Be the first
Looked up: 2 h ago

Saved setup from 2 h ago

Start here

Website ↗langflow.orgThe project's own site.In the browser ↗Open in GitHub CodespacesThe repo ships a dev container, so nothing to install.

Will it work on my device?

Yes, with Docker on macOS

It's a self-hosted app: the README runs it with Docker, and you open it in your browser.
On macOS that means installing Docker Desktop first.

Checking for

Run it with Docker

A self-hosted app: Docker runs it on your computer and you open it in the browser. Needs Docker Desktop (or Docker Engine on Linux). Run docker compose commands inside the cloned repo folder.

Docker

docker run -p 7860:7860 -e LANGFLOW_SUPERUSER_PASSWORD langflowai/langflow:latest

From the README, exactly as the maintainers wrote it.

Did you get it running?

No reports for macOS yet.

Still stuck? Get a written guide

Claude reads the 15 key files and writes a step-by-step guide for macOS. Once written, it's saved for everyone.

Parts list

1×Node.js 22runtime
1×Python >=3.10,<3.15runtime
1×npm package manager
1×uv package manager
1×MongoDB service
1×Redis service

60× settings in .env

DOMAIN
STACK_NAME
TRAEFIK_PUBLIC_NETWORK
TRAEFIK_TAG
TRAEFIK_PUBLIC_TAG
LANGFLOW_LOG_LEVEL
LANGFLOW_SUPERUSER
LANGFLOW_SUPERUSER_PASSWORDsecret
LANGFLOW_NEW_USER_IS_ACTIVE
BACKEND_URL
RABBITMQ_DEFAULT_USER
RABBITMQ_DEFAULT_PASSsecret
DB_USER
DB_PASSWORDsecret
DB_HOST
DB_PORT
DB_NAME
POSTGRES_USER
POSTGRES_PASSWORDsecret
POSTGRES_DB
POSTGRES_PORT
LANGFLOW_REDIS_DB
LANGFLOW_REDIS_EXPIRE
LANGFLOW_REDIS_PASSWORDsecret
FLOWER_UNAUTHENTICATED_API
BROKER_URLoptional
RESULT_BACKENDoptional
C_FORCE_ROOToptional
PGADMIN_DEFAULT_EMAIL
PGADMIN_DEFAULT_PASSWORDsecret
GP_USER_ID
GP_PASSWORDsecret
GP_INSTANCE
GP_BUNDLE
LANGFLOW_CONFIG_DIR
LANGFLOW_SAVE_DB_IN_CONFIG_DIR
LANGFLOW_DATABASE_URL
LANGFLOW_ALEMBIC_LOG_TO_STDOUT
LANGFLOW_DATABASE_CONNECTION_RETRY
LANGFLOW_LANGCHAIN_CACHE
LANGFLOW_HOST
LANGFLOW_WORKERS
LANGFLOW_PORT
LANGFLOW_LOG_FILE
LANGFLOW_LOG_ROTATION
LANGFLOW_FRONTEND_PATH
LANGFLOW_OPEN_BROWSER
LANGFLOW_REMOVE_API_KEYSsecret
LANGFLOW_CACHE_TYPEoptional
LANGFLOW_ENABLE_SUPERUSER_CLI
LANGFLOW_API_KEY_SOURCEsecret
LANGFLOW_API_KEYsecret
LANGFLOW_RATE_LIMIT_PER_MINUTE
LANGFLOW_PUBLIC_FLOW_RATE_LIMIT_PER_MINUTE
LANGFLOW_RATE_LIMIT_STORAGE_URI
LANGFLOW_RATE_LIMIT_TRUST_PROXY
LANGFLOW_STORE_ENVIRONMENT_VARIABLES
LANGFLOW_SSRF_PROTECTION_ENABLED
LANGFLOW_SSRF_ALLOWED_HOSTS
LANGFLOW_MCP_COMPOSER_ENABLED

Share this manual

Is this your repo?

Add a badge to your README so newcomers find these steps.

[![Setup manual](https://gitmanual.com/langflow-ai/langflow/badge.svg)](https://gitmanual.com/langflow-ai/langflow)

Good to know

Dev Container config found — you can open it in VS Code Dev Containers or GitHub Codespaces for a zero-setup environment.
Makefile has a make init target — it may automate most of these steps.
Has AGENTS.md — instructions for coding agents. You can open Claude Code (or another agent) in the cloned folder and ask it to do the setup for you.
Nested projects: docs/package.json, scripts/gp/requirements.txt, src/backend/base/pyproject.toml, src/bundles/amazon/pyproject.toml and 11 more

Files we read (15)

.devcontainer/devcontainer.json

.env.example

.github/workflows/a11y-unit-tests.yml

.github/workflows/backend-unit-tests.yml

.github/workflows/ci-scripts-test.yml

.github/workflows/ci.yml

.github/workflows/cross-bundle-test.yml

.github/workflows/cross-platform-test.yml

DEVELOPMENT.md

Makefile

README.md

deploy/.env.example

package.json

pyproject.toml

scripts/gp/.env.example

Branch main · 11,878 files in the repo