Chainlit

Chainlit's Python framework lets developers self-host conversational AI applications and provide a browser chat interface around their own application logic. Its OpenAI assistant example uses the OpenAI Python SDK’s standard connection, sending model requests to OpenAI’s cloud service. Self-hosting the chat server and supplying model inference are separate choices.

The framework suits teams building a chat product around an existing AI workflow. Developers can deploy a standalone web app, embed a copilot in another product, or deliver a bot through Slack, Discord or Teams. It can run with FastAPI servers and custom React applications.

Developers control the interface. They can customize the frontend and create their own chat components. Authentication supports simple methods as well as OAuth through providers including GitHub, Google, Azure and Okta.

Integrations include LangGraph and LlamaIndex for application workflows, alongside OpenAI, Mistral and HuggingFace. Cookbook examples also cover LangChain, ChromaDB and Pinecone. Developers configure model access separately from the self-hosted chat server.

The framework is open source under Apache 2.0 and is community-maintained. Community maintainers handle code review, releases and security.