Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
Python agentagentic-aiagentic-frameworkagentic-workflowaiautomationclaudedeepseekgenaigptllmlow-codemcpnextjsno-codeopenaipythonskillsworkflow
docs(readme): update docker quick start requirements (#45394)
-LAN-eef50ad25952
diff --git a/README.md b/README.mdindex e8572f93797..1f2414728c9 100644--- a/README.md+++ b/README.md@@ -72,16 +72,28 @@ Dify is an open-source LLM app development platform. Its intuitive interface com<br/>-The easiest way to start the Dify server is through [Docker Compose](docker/docker-compose.yaml). Before running Dify with the following commands, make sure that [Docker](https://docs.docker.com/get-docker/) and Docker Compose v2.24.0 or later are installed on your machine:+The easiest way to start the Dify server is through [Docker Compose](docker/docker-compose.yaml). Install [Docker](https://docs.docker.com/get-docker/) with a running daemon, Docker Compose v2.35.0 or later, and OpenSSL.++For a new deployment, run the following commands from the repository root. For an existing deployment, preserve your `.env` and follow the [upgrade guidance](docker/README.md#review-configuration-after-an-upgrade).```bash-cd difycd dockercp .env.example .env+openssl rand -hex 32+```++Open `.env` and set `DIFY_AGENT_LOCAL_SANDBOX_AUTH_TOKEN` to the generated value. Keep the default `COMPOSE_PROFILES` value for the bundled services. Service defaults load automatically; no additional configuration files are required.++From the same `docker` directory, start the services:++```bashdocker compose up -d+docker compose ps --all```-After running, you can access the Dify dashboard in your browser at [http://localhost/install](http://localhost/install) and start the initialization process.+Once the services are running, open [http://localhost/install](http://localhost/install) to complete the initial setup. The one-time `init_permissions` service is expected to exit with code `0`.++For optional settings and service overrides, see the [Docker deployment guide](docker/README.md#configure-dify).### Seeking help