Langflow release notes - Langflow

import Icon from "@site/src/components/icon"; import McpIcon from '@site/static/logos/mcp-icon.svg';

This page summarizes significant changes to Langflow in each release. For all changes, see the Changelog.

Due to strict SemVer requirements, Langflow Desktop can have different patch versions than the core Langflow OSS Python package, but the major and minor versions are aligned.

Prepare to upgrade

:::warning Whenever possible, the Langflow team recommends installing new Langflow versions in a new virtual environment or VM before upgrading your primary installation. This allows you to import flows from your existing installation and test them in the new version without disrupting your existing installation. In the event of breaking changes or bugs, your existing installation is preserved in a stable state. If you are upgrading Windows Desktop to 1.6.0, don't auto-upgrade with the in-app Update button. Instead, follow the instructions in Known issue: Don't auto-upgrade Windows Desktop. :::

To avoid the impact of potential breaking changes and test new versions, the Langflow team recommends the following upgrade process:

Recommended: Export your projects to create backups of your flows:

bash

curl -X GET \
"$LANGFLOW_SERVER_URL/api/v1/projects/download/$PROJECT_ID" \
  -H "accept: application/json" \
  -H "x-api-key: $LANGFLOW_API_KEY"

To export flows from the visual editor, see Import and export flows.

Install the new version:
- Langflow OSS Python package: Install the new version in a new virtual environment. For instructions, see Install and run the Langflow OSS Python package.
- Langflow Docker image: Run the new image in a separate container.
- Langflow Desktop: To upgrade in place, open Langflow Desktop, and then click Upgrade Available in the Langflow header. If you want to isolate the new version, you must install Langflow Desktop on a separate physical or virtual machine, and then import your flows to the new installation.
Import your flows to test them in the new version, upgrading components as needed.

When upgrading components, you can use the Create backup flow before updating option if you didn't previously export your flows.
If you installed the new version in isolation, upgrade your primary installation after testing the new version.

If you made changes to your flows in the isolated installation, you might want to export and import those flows back to your upgraded primary installation so you don't have to repeat the component upgrade process.

1.9.x

Highlights of this release include the following changes. For all changes, see the Changelog.

New features and enhancements

Langflow MCP client for Bob (IBM) and Claude Code

The Settings page now includes <Icon name="Terminal" aria-hidden="true"/> Langflow MCP Client, with instructions to connect Bob (IBM) and Claude Code to your Langflow instance. For more information, see Langflow MCP client.
MCP Tools: register servers first, and then add from the MCP sidebar

MCP Tools is no longer added from the Agents component list. Register each MCP server under Settings > *MCP Servers, or from the flow editor <McpIcon /> MCP sidebar. Each saved server appears as a unique MCP Tools component that can be dragged to the canvas. For more information, see Use Langflow as an MCP client.
Flow DevOps Toolkit SDK

Use the Flow DevOps Toolkit SDK to manage local and remote flows with Git-style terminal commands. For more information, see the Langflow Flow DevOps Toolkit SDK.
Renamed Data and DataFrame types

The Data object is now named JSON, and the DataFrame object is now named Table. Flows using Data or DataFrame are backwards compatible. For more information, see Langflow data types.
Renamed Data Operations and DataFrame Operations components

The Data Operations component is now the JSON Operations component, and the DataFrame Operations component is now the Table Operations component.
Flow version history in the visual editor

You can now save point-in-time versions of a flow from Version History, preview saved versions in read-only mode, and restore an earlier version to your working draft. For more information, see Build flows.
Enabled tool calling for Gemini 3 preview models

Tool calling is enabled for the following Google Gemini 3 preview models: gemini-3.1-pro-preview, gemini-3-pro-preview, gemini-3-flash-preview, and gemini-3-pro-image-preview.
Build components with Langflow Assistant

Langflow Assistant is a graph-aware co-pilot that can create components from natural language prompts, directly within the Langflow workspace. For more information, see Langflow Assistant.
Vulnerability reporting now uses HackerOne

Security reports should now be filed through IBM's HackerOne program. Please do not report security vulnerabilities through public GitHub issues or GitHub security advisories. For the full policy and what to include in a report, see the Langflow Security Policy.
Disable custom components

Set LANGFLOW_ALLOW_CUSTOM_COMPONENTS=false to disable custom components and in-editor editing of component code. For more information, see Block custom components.
Deploy flows to watsonx Orchestrate (beta)

In Langflow 1.9.1, Langflow flows can now be published to IBM watsonx Orchestrate as tools that a watsonx Orchestrate agent can call. This workflow packages a selected flow version for use in IBM watsonx Orchestrate. For more information, see Deploy Langflow on watsonx Orchestrate.

As of Langflow 1.9.2, this feature is behind a feature flag. To enable it, set LANGFLOW_FEATURE_WXO_DEPLOYMENTS=true before starting Langflow.
Policies component (beta)

The Policies component uses ToolGuard to generate guard code from natural-language business policies and apply it to agent tools. For more information, see Policies (Beta).

1.8.x

For 1.8.x release notes, see the 1.8.x documentation.

Earlier releases

See the Changelog.