Chainlit home page
Search...
⌘K
Github
Join Discord
Join Discord
Search...
Navigation
Get Started
Overview
Documentation
Examples
API Reference
Chainlit Help
Get Started
Overview
Installation
In Pure Python
Integrations
Deploy
Overview
Platforms
Basic Concepts
Chat Life Cycle
Starters
Message
Step
User Session
Element
Action
Command
Advanced Features
Streaming
MCP Servers
Ask User
Multi-Modality
Chat Profiles
Chat Settings
Testing & Debugging
Data Persistence
Overview
Chat History
Human Feedback
Open Source Data Layers
Tags & Metadata
Authentication
Overview
Password
Header
OAuth
Customisation
Overview
Translation
Avatars
Logo and Favicon
Theme
JS
CSS
Backend
Config
Environment Variables
Command Line Options
Guides
Async / Sync
Migrate to Chainlit v2.0.0
On this page
Key features
Integrations
Get Started
Overview
Chainlit is an open-source Python package to build production ready Conversational AI.
Build Conversational AI with Chainlit
Key features
Build fast:
Get started in a couple lines of Python
Authentication:
Integrate with corporate identity providers and existing authentication infrastructure
Data persistence:
Collect, monitor and analyze data from your users
Visualize multi-steps reasoning:
Understand the intermediary steps that produced an output at a glance
Multi Platform:
Write your assistant logic once, use everywhere
Integrations
Chainlit is compatible with all Python programs and libraries. That being said, it comes with a set of integrations with popular libraries and frameworks.
LangChain
Learn how to use any LangChain agent with Chainlit.
OpenAI
Learn how to explore your OpenAI calls in Chainlit.
OpenAI Assistant
Learn how to integrate your OpenAI Assistants with Chainlit.
Mistral AI
Learn how to use any Mistral AI calls in Chainlit.
Semantic Kernel
Learn how to integrate your Semantic Kernel code with Chainlit.
Llama Index
Learn how to integrate your Llama Index code with Chainlit.
Autogen
Learn how to integrate your Autogen agents with Chainlit.
Was this page helpful?
Yes
No
Suggest edits
Raise issue
Installation
Assistant
Responses are generated using AI and may contain mistakes.