Search

More Filters

Show More
Add Listing
Go Back

openai agents js

0
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

This repository is a TypeScript/JavaScript port of the OpenAI Agents SDK intended for Node.js environments. It provides a feature-parity implementation of the official Python agents SDK so developers can build multi-agent LLM workflows using familiar API design and patterns in TypeScript. The library is provider-agnostic and documented to work with OpenAI Responses and Chat Completions APIs as well as over 100 other LLMs. Core concepts implemented include configurable Agents, Handoffs for transferring control between agents, Guardrails for input and output validation, Tracing for run inspection, and support for tools and function calls. The README includes examples such as a hello world agent, handoff workflows, function tools for calling code, and Model Context Protocol integrations like a filesystem MCP server. Note that the project is archived and marked deprecated by the author.

Links

Stars
85
App URL
https://github.com/yusuf-eren/openai-agents-js
Github Repository
https://github.com/yusuf-eren/openai-agents-js/blob/main/README.md

Categorization

App Details

Features
The SDK offers modular Agents with instructions, tools, and handoffs, plus deterministic and iterative agent loop execution using Runner.run. It supports function-style tools through a FunctionTool construct and includes examples showing parameter schemas and tool invocation handlers. Handoffs allow controlled agent-to-agent transfers. Guardrails provide configurable safety and validation for inputs and outputs. Tracing is built in and extensible so runs can be tracked, debugged, and exported to external destinations. MCP support is available to connect agents to external services via Model Context Protocol servers, for example a filesystem MCP with list and read tools. The library is provider-agnostic, supporting OpenAI APIs and many other LLMs. Development scripts include npm install, build, and test commands and an examples directory for common patterns.
Use Cases
This SDK helps developers rapidly create and iterate on multi-agent LLM workflows in Node.js by providing a ready-made framework that mirrors the official Python Agents API. It reduces implementation overhead by including core patterns such as the agent loop, tool invocation, handoffs between agents, and guardrails for safer outputs. MCP integration simplifies connecting agents to external resources like filesystems and other services using a standardized interface. Tracing and examples make it easier to observe behavior, debug issues, and optimize interactions. The FunctionTool pattern enables structured tool calls with JSON schema validation. Because it is provider-agnostic and aligns with the official SDK, teams can port ideas between languages and experiment with many models without redesigning their agent architecture.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1230)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (766)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

yutu

0 (0 review)
listing image

cyber-doctor

0 (0 review)
listing image

LLM-Powered-RAG-System

0 (0 review)
listing image

vibevideo-mcp

0 (0 review)
listing image

xpert

0 (0 review)

Featured Listings

Tags

Please fill the required fields*