Langflow OSS 1.10 is released! This version expands Langflow Assistant's capabilities, introduces long-term memory for flows with Memory bases, adds configurable vector database backends for knowledge bases, and brings the Langflow interface to seven languages.
Core features
-
Langflow Assistant: build complete flows
-
Memory bases
-
Database connectors for knowledge bases
-
Internationalization
Production and developer updates:
- Redis-backed job queue for multi-worker deployments
- Python 3.14 support
- IBM Db2 component
- File System component
- Extension bundles
- …and more
Let's dig into some of these features to see how they make Langflow more powerful for production deployments and long-running AI workflows.
Langflow Assistant: build complete flows
Langflow Assistant can now build entire flows, not only individual components. Describe what you want to build in natural language, and the assistant generates a complete, connected flow ready to run in the canvas. This helps users move faster from an idea to a working AI workflow.
For more information, see Build flows and components with Langflow Assistant.
Memory bases
Memory bases are per-flow vector stores that automatically ingest conversation messages. Unlike Langflow's session-scoped memory, memory bases persist conversation context across sessions in a flow. Connect agents to a Memory Base component to retrieve conversation context from the vector store.
For more information, see Manage memory bases.
Database connectors for knowledge bases
Knowledge bases now support configurable vector database backends through DB Providers configured in Settings → DB Providers. Available providers include Chroma, Chroma Cloud, and OpenSearch. This gives users more flexibility to choose where embeddings are stored and manage RAG workflows beyond local Chroma storage.
For more information, see Manage vector data.
Internationalization
The Langflow interface is now available in multiple languages. To change the display language, click your Profile Picture, select Settings, and then select a language from the Language dropdown.
Available languages include English, French (Français), Spanish (Español), German (Deutsch), Portuguese (Português), Japanese (日本語), and Chinese (中文).
Redis-backed job queue for multi-worker deployments
Langflow now supports a Redis-backed job queue that allows flow build events to be shared across multiple Gunicorn/Uvicorn workers.
The default asyncio in-memory queue is not changed.
For more information, see Deploy Langflow with multiple workers.
Python 3.14 support
Langflow now supports Python 3.10 through 3.14 on macOS, Linux, and Windows. The Langflow Docker images now use Python 3.14.
IBM Db2
The lfx-ibm bundle now includes an IBM Db2 component, which you can add to flows to connect and query IBM Db2 databases.
This makes it easier for enterprise users running Db2 to integrate their existing data infrastructure into Langflow workflows.
For more information, see the lfx-ibm bundle documentation.
File System component
The File System component gives agents sandboxed read/write access to files on disk. An optional Read Only mode restricts the agent to read and search operations only.
For more information, see File System.
Extension bundles
Langflow 1.10 introduces the Extension bundles model. Component providers are packaged as standalone pip packages, and versioned and released independently from the core langflow package.
Four bundles ship in the 1.10 release: lfx-arxiv, lfx-docling, lfx-duckduckgo, and lfx-ibm. All four are still included as dependencies of the langflow metapackage, so uv pip install langflow will still install them. Nothing changes for existing users in release 1.10.
This change is being called out because in release 1.11, more components will move to bundles and be removed as automatic dependencies of langflow.
This means components that are currently included with uv pip install langflow will no longer be included after upgrading to 1.11.
You'll need to install their bundle packages manually for those components to appear in the canvas.
Saved flows will continue to open normally.
However, if you reference component class names in code, read component type identifiers from raw flow JSON, use lfx.components.<provider> import paths, or pin individual component packages in deployment scripts, plan for those updates before upgrading to 1.11.
For more information, see Langflow Extensions overview.
There's more to come
For more on all the changes that have been released in Langflow OSS 1.10, check out 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 1.10 open-source package. Check out the 1.10.0 release on GitHub and get building!
Langflow Desktop 1.10 will be released soon. In the meantime, visit Download Langflow Desktop to install the current desktop version.
