What is the primary purpose of the chatkit-backend skill?

It provides a standardized pattern for building FastAPI backends that support real-time streaming and conversation history specifically for applications using the OpenAI ChatKit frontend.

Does this skill support tool execution streaming?

Yes, it includes specific event formats for yielding tool_call and tool_result events through the SSE stream so the UI can display agent actions in real-time.

Which database libraries does this skill utilize?

The skill is designed to work with SQLModel and FastAPI's dependency injection system to handle conversation and message persistence.

Is this skill compatible with LLMs other than OpenAI?

While it follows the ChatKit format, it can be integrated with various models (like Gemini or Anthropic) via the OpenAI Agents SDK or LiteLLM wrappers.

ChatKit FastAPI Backend

Name: ChatKit FastAPI Backend
Author: maneeshanif

bymaneeshanif

Desarrollo de API

Implements high-performance FastAPI backends for OpenAI ChatKit with real-time SSE streaming and agent integration.

Acerca de

This skill provides a production-ready blueprint for building robust FastAPI backends tailored specifically for the OpenAI ChatKit frontend. It streamlines the implementation of Server-Sent Events (SSE) for real-time streaming, automated conversation persistence using SQLModel, and seamless integration with the OpenAI Agents SDK. By providing standardized message formats and streaming protocols, it allows developers to quickly deploy AI-powered backends that handle everything from simple text responses to complex multi-turn tool executions.

Características Principales

Standardized ChatKit-compatible message schemas and error handling
0 GitHub stars
Real-time SSE streaming for text, thinking, and tool execution events
Seamless integration with OpenAI Agents SDK and LiteLLM
Pre-configured FastAPI routers for rapid project bootstrapping
Persistent conversation and message storage using SQLModel and FastAPI

Casos de Uso

Adding streaming capabilities to existing Python APIs for real-time user feedback
Building a custom AI agent backend that interfaces with the OpenAI ChatKit UI
Implementing multi-turn conversation history for AI-driven web applications

Acerca de

Características Principales

Standardized ChatKit-compatible message schemas and error handling
0 GitHub stars
Real-time SSE streaming for text, thinking, and tool execution events
Seamless integration with OpenAI Agents SDK and LiteLLM
Pre-configured FastAPI routers for rapid project bootstrapping
Persistent conversation and message storage using SQLModel and FastAPI

Casos de Uso

Adding streaming capabilities to existing Python APIs for real-time user feedback
Building a custom AI agent backend that interfaces with the OpenAI ChatKit UI
Implementing multi-turn conversation history for AI-driven web applications