Langflow 1.13 released: Audit logs, connections, and concurrent editing

Langflow OSS 1.13 is released! This version adds audit logging, reusable connections, and concurrent editing checks.

Audit logging records who changed a flow or project. Connections let you connect an account once and reuse it across flows. Concurrent editing keeps one user's save from replacing another's when a flow is being edited by more than one user.

Before you upgrade

LANGFLOW_AUTO_LOGIN is now false by default. You must set a superuser password before you start 1.13, or you may not be able to sign in. For more information, see the Breaking change section below, and the release notes.

Audit logging

Langflow can record an append-only history of flow and project operations, including who attempted a change, on which resource, when, how it completed, and a description of what was written.

To enable it, set the following environment variable before starting Langflow:

LANGFLOW_AUDIT_ENABLED=true

Query audit events with GET /api/v1/flows/audits and GET /api/v1/projects/audits.

For more information, see Audit logging.

Connections

Langflow stores Google Workspace, Microsoft 365, and Slack accounts as reusable connections.

Connect an account once, and then re-use that same connection in any flow.

For more information, see Connections.

Concurrent editing

Langflow protects a flow that is open by more than one user. When another save has already updated the flow, your changes remain on the canvas until you review them.

For more information, see Concurrent editing.

Breaking change: LANGFLOW_AUTO_LOGIN is false by default

Official Python packages, tagged source archives, and Docker images now set LANGFLOW_AUTO_LOGIN=false.

This change affects new installations and upgrades differently.

• Before upgrading an existing Langflow installation, see prepare Langflow account for password sign-in.

• If you already upgraded Langflow to version 1.13 and can't sign in, see recover access.

• If you're installing Langflow for the first time, set a superuser password in a .env file before you start Langflow:

  1. Create a .env file and set LANGFLOW_SUPERUSER_PASSWORD:

     LANGFLOW_SUPERUSER_PASSWORD=<your-password>
     

     The default username is langflow. To set a different username, set LANGFLOW_SUPERUSER=<your-username>.

  2. Start Langflow with that file.

     To start Langflow from Python package, run:

     uv run langflow run --env-file .env
     

     To start Langflow with Docker, run:

     docker run -p 7860:7860 \
       --env-file .env \
       -v langflow-data:/app/langflow \
       -e LANGFLOW_CONFIG_DIR=/app/langflow \
       -e LANGFLOW_SAVE_DB_IN_CONFIG_DIR=true \
       langflowai/langflow:latest
     

     The volume keeps the database, secret key, and uploaded files when the container is recreated. For more information, see Upgrade the Langflow Docker image.

  3. Sign in at http://localhost:7860 with the username langflow or your configured LANGFLOW_SUPERUSER, and the password from your .env file.

You can still set LANGFLOW_AUTO_LOGIN=true for trusted environments.

For more information, see API keys and authentication.

Possible breaking change: Chroma DB and Local DB are legacy

Langflow 1.13 stores local Knowledge and Memory in SQLite, instead of a local Chroma database. The Chroma DB and Local DB components are legacy.

Replace Chroma DB and Local DB with a knowledge base, or with a supported remote vector store.

Back up the application database and the knowledge-base directory before you upgrade.

For more information, see Upgrade Knowledge and Memory storage.

There's more to come

For the full list of changes in Langflow OSS 1.13, see the release notes or the full release on GitHub.

We're committed to continuously improving Langflow, and your input is crucial to this process. If you want to get more involved you can:

• Join our Discord community to network with other developers
• Explore our GitHub repository to contribute to the project or 🌟 the project
• Subscribe to our YouTube channel for step-by-step guides on using Langflow
• Stay updated on the latest AI trends and insights by subscribing to the AI++ newsletter

We're excited to see the projects you'll create with the Langflow 1.13 open-source package. Check out the 1.13.0 release on GitHub and get building!

Langflow Desktop 1.13 will be released soon. In the meantime, visit Download Langflow Desktop to install the current desktop version.