We’ve been coding at a pace of ~3000 code lines a day, and it’s incredibly rewarding to see developers from all over the world already using Langflow to speed up their AI projects.
Vision: Multi-Agent AI and RAG
The idea for Langflow 1.0 is to make it the most powerful visual framework for building RAG and multi-agent applications out there — open-source, fully customizable and with unrestricted component control. Let’s dive into some of the key new features!
Output Preview
Langflow now includes an output visualizer for components that opens a pop-up screen. This allows you to easily inspect and monitor transmissions between components, providing instant feedback on your workflows.
Memory Management
Langflow allows every chat message to be stored, and a single flow can have multiple memory sessions. This enables you to create multiple “memories” for agents to store and recall specific information as needed.
You can edit and remove previous messages to inspect and validate a model’s response behavior. Control, explore, and manage conversation histories to get your models acting just right.
Component Freeze 🥶
Component output freezing is back in Langflow, and it’s cooler than ever!
Once a component runs, you can now lock its previous output state to prevent it from re-running.
Avoid spending extra tokens and remove repetition when output should be constant — plus it's great for debugging and prototyping!
Custom Endpoint Name
Now you can pick a custom name for your endpoint used to call your flow from the API.
And more…
Langflow is now multi-modal. It can handle images and more soon! We’ve also improved project organization, global variables and overall settings.
Remember that this is all still very early, so expect some (or many) bugs! Your feedback is crucial so please keep sending it.
See our Release Notes for more new features and capabilities and make sure to star our GitHub repo! 🌟
Happy Building,
The Langflow Team
