About openai-agents-chat-demo
A web chat demo built with the OpenAI Agents framework, for users exploring conversational agents with custom tools. It includes conversation history and context management.
Key features
- 01OpenAI Agents-based chat
- 02Custom function tools
- 03Web interface
- 04Conversation history and context
Use cases
- 01Prototyping a chat agent
- 02Adding custom functions to conversations
MCP support
The project tagline describes integration with an MCP server, but the README does not specify how that integration works.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEopenai-agents-chat-demo
openai agents chat demo. integration custom llm and mcp server and function tool
基于openai-agents框架实现的聊天对话机器人。
功能特点
- 使用OpenAI Agents框架实现智能对话
- 支持自定义工具函数扩展能力
- 提供简洁的Web界面进行交互
- 支持对话历史记录和上下文管理
安装与使用
环境要求
- Python 3.8+
- llm API密钥
安装依赖
pip install -r requirements.txt
配置
- 查看config，进行自定义配置
运行
python app.py
访问 http://localhost:8050 开始使用聊天机器人。
项目结构
app.py: Web应用主入口agent.py: 聊天代理实现config.py: 配置文件templates/: HTML模板static/: 静态资源文件utils/: 工具函数
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.