material.md

Introducing Dify Agent (Experimental): A New Agent Experience in Dify

Warning

You should provide Dify Agent services ⚠️only to trusted, non-malicious users⚠️.

As many of you know, the shell-based LLM agent paradigm has brought a major leap in agent capabilities and changed how we think about agents. Meanwhile, Skills provide a standardized way to package and distribute capabilities, making it easier to build powerful agents.

Today, we are experimentally launching Dify Agent. Like other leading agents, it runs in a Linux sandbox. This release includes:

• A builder for creating Dify Agents

  • You can build Dify Agents through the UI: set a base prompt, upload Skills and files, and connect tools and knowledge from the Dify ecosystem.
  • We also provide an agent that helps you build Dify Agents. Through conversation, it can configure the Linux sandbox environment, install required packages, and create new Skills and files that your Dify Agent can use later.

• Dify Workflow integration for Dify Agent

  • You can use an existing Dify Agent in a Dify Workflow, or temporarily create an inline Dify Agent. It will execute the task defined by the workflow node, generate the required output, and pass it to the next node.

• A new web app experience

  • The Dify Agent you build can be published and used as a web app. While the user experience remains familiar, it is now powered by Dify Agent.

Docs: https://docs.dify.ai/en/self-host/use-dify/build/new-agent/overview

Limitation

Please note that in the current experimental release, all Dify Agents run in the same sandbox. This means:

• Under normal circumstances, each Dify Agent configures its environment and executes tasks within its own workspace without interfering with others.
• However, with simple instructions, any Dify Agent can read or interfere with the environments and data of other Dify Agents, including user data.

Strict isolation will be implemented in a future release. For now，

Warning

You should provide Dify Agent services ⚠️only to trusted, non-malicious users⚠️.

Similarly, because Dify Agent is not fully ready yet, you may find that some features are not available for Dify Agent. For example, Dify Workflow DSL export is unavailable when the workflow contains nodes that reference Dify Agent.

Upgrade Notes

Docker Compose

For Docker Compose deployments, this release adds two new services: agent_backend and local_sandbox.

No manual changes to environment variables are required. However, for production or staging-like environments, replace the default placeholder value of DIFY_AGENT_SERVER_SECRET_KEY with a secure secret key.

Database

This release includes new database migrations. After upgrading, run:

flask db upgrade