Python + Markdown framework for building internal apps.
Last updated Jul 8, 2026
112
Stars
4
Forks
0
Issues
+1
Stars/day
Attention Score
77
Topics
Language breakdown
Python 96.3%
TypeScript 1.7%
CSS 1.6%
HTML 0.2%
MDX 0.1%
▸ Files
click to expand
README

Features
Morph is a python-centric full-stack framework for building and deploying AI apps.
- Fast to start 🚀 - Allows you to get up and running with just three commands.
- Deploy and operate 🌐 - Easily deploy your AI apps and manage them in production. Managed cloud is available for user authentication and secure data connection.
- No HTML/CSS knowledge required🔰 - With Markdown-based syntax and pre-made components, you can create flexible, visually appealing designs without writing a single line of HTML or CSS.
- Customizable 🛠️ - Chain Python and SQL for advanced AI workflows. Custom CSS and custom React components are available for building tailored UI.
Quick start
- Install morph
pip install morph-data
- Create a new project
morph new
- Start dev server
morph serve
- Visit
http://localhsot:8080on browser.
How it works
Understanding the concept of developing an AI app in Morph will let you do a flying start.
- Develop the AI workflow in Python and give it an alias.
- Create an .mdx file. Each .mdx file becomes a page of your app.
- Place the component in the MDX file and specify the alias to connect to.
.
├─ pages
│ └─ index.mdx
└─ python
└─ chat.py
Building AI Apps
A little example
- Create each files in
pythonandpagesdirectories.
import morph
from morph import MorphGlobalContext
from morphlib.stream import streamchat
from langchain_openai import ChatOpenAI
from langchain_core.messages import HumanMessage
@morph.func def langchain_chat(context: MorphGlobalContext): llm = ChatOpenAI(model="gpt-4o") messages = [HumanMessage(context.vars["prompt"])] for token in llm.stream(messages): yield stream_chat(token.content)
MDX: Define the page and connect the data.
# 🦜🔗 Langchain Chat
<Chat postData="langchain_chat" height={300} />
- Run
morph serveto open the app!
Documentation
Visit https://docs.morph-data.io for more documentation.
Contributing
Thanks for your interest in helping improve Morph ❤️
- Before contributing, please read the CONTRIBUTING.md.
- If you find any issues, please let us know and open an issue.
Lisence
Morph is Apache 2.0 licensed.
🔗 More in this category