OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Morph

Morph is an Apache 2.0-licensed, Python-centric full-stack framework for building AI applications. Developers define workflows in Python and create app pages in MDX, connecting interface components to workflows by alias. It includes pre-made components and supports Python and SQL workflows, with custom CSS and React components available for tailored interfaces.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Morph — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Morph when you want to pair Python-based AI or data workflows with MDX app pages and connect those workflows to interface components. Its documented LangChain example shows a streaming chat pattern; the local CLI flow supports project creation and development.

Who it is for

  • Developers building internal AI applications with Python workflows and MDX pages.
  • Teams creating data analysis or visualization interfaces that need custom React components.
  • Developers connecting AI workflows to chat or other page components.

Documented uses

  • Create app pages with Markdown-based MDX and pre-made components.
  • Connect Python workflows to page components using workflow aliases.
  • Build a LangChain chat interface that streams model output into a Morph page.
  • Combine Python and SQL in application workflows.
  • Customize interfaces with CSS or React components.
Before you choose

Requirements & limits

The repository documents local development through the Morph CLI and describes managed cloud as available for user authentication and secure data connections. The project is Apache 2.0 licensed.

  • The documented development flow uses Python workflow files and MDX pages connected by aliases.
  • Pre-made components reduce the need to write HTML or CSS for basic layouts; custom CSS and React are available for more tailored UI.
  • The LangChain chat example uses streaming and requires model-provider setup and credentials.
  • The README documents local server startup separately from deployment and production operation.
  • The project is licensed under Apache 2.0.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up a local Morph project

Install Morph, create a project, and start its local development server.

Before you start

  • Python package installation with pip
  • A terminal with the Morph CLI available

Steps

  1. Install the package with the command below.

    Documented command
    pip install morph-data

  2. Create a project with morph new.

  3. Start the development server with morph serve.

  4. Open the local address http://localhost:8080 in a browser; the README spells it as localhsot, so check the address if it does not open.

Expected outcome

A local Morph development server is started for the project.

Guide limitations

  • These instructions cover local development, not production deployment.
  • The README contains a typo in its stated local browser address.
Documentation 1 ↗
Source-based practical guide

Connect a LangChain streaming chat to an MDX page

Define a LangChain chat workflow and connect it to a Morph Chat component.

Before you start

  • A Morph project with Python workflow and MDX page files
  • LangChain packages used by the example, including langchain_openai and langchain_core
  • Model provider setup and credentials for ChatOpenAI

Steps

  1. Create a Python function decorated with @morph.func and give it a workflow name such as langchain_chat.

  2. Read the prompt from context.vars["prompt"], stream model output, and yield each token through stream_chat.

  3. Add a Chat component to an MDX page and set its postData value to the workflow name.

  4. Start the app with morph serve.

Expected outcome

The documented pattern connects an MDX chat component to a Python LangChain workflow that streams model output.

Guide limitations

  • The example depends on model provider configuration and credentials.
  • The repository example documents the pattern; it does not specify additional provider setup steps.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
morph-data/morph · Official homepage title · retained in its source language
How we review sourcesSuggest a correction