Dify is an open-source platform for developing LLM applications. Its intuitive interface combines agentic AI workflows, RAG pipelines, agent capabilities, model management, observability features, and more—allowing you to quickly move from prototype to production.
Scenario | Recommended Install Method |
---|---|
I just want a working Dify instance ASAP (demo, PoC, small team) | Docker Compose – one command boots all 11 containers |
I need to hack the code, contribute or heavily customise | Run from local source – spin up middle-wares with Docker, start back- & front-end manually |
Total time: ±5 min on a modern laptop
Clone and enter repo
git clone <https://github.com/langgenius/dify.git>
cd dify/docker
Create environment file
cp .env.example .env
# (edit ports, domain names or provider keys now if you wish)
Launch
docker compose up -d # Compose v2
# or
docker-compose up -d # Compose v1
Eleven containers (api
, worker
, web
, plus Postgres, Redis, Weaviate, Nginx …) come up; verify with docker compose ps
. Dify Docs
Initialise
URL | Purpose |
---|---|
http://localhost/install |
one-time wizard → create Admin |
http://localhost |
normal sign-in UI |
Upgrade later
cd dify/docker
docker compose down
git pull origin main
docker compose pull
docker compose up
Remember to diff .env
against new .env.example
after each release. Dify Docs
cd dify/docker
cp middleware.env.example middleware.env
docker compose -f docker-compose.middleware.yaml up -d