Search

More Filters

Show More
Add Listing
Go Back

openai agents js

0
New
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

The repository provides the OpenAI Agents SDK for JavaScript and TypeScript, a lightweight framework for building and orchestrating multi-agent workflows. It is designed for developers who need to compose agents that use LLMs, call external tools, hand off control between specialized agents, and enforce input/output validation. The SDK is provider-agnostic and supports OpenAI APIs as well as broader model support through an adapter. It includes realtime voice agent support for browser environments, a separate optimized browser package, and local MCP server support for giving agents access to local tools. The project includes examples, documentation, and a tracing UI to inspect and debug agent runs. Supported runtimes include Node.js 22+, Deno, and Bun, with experimental Cloudflare Workers compatibility.

Links

Stars
1037
App URL
https://github.com/openai/openai-agents-js
Github Repository
https://github.com/openai/openai-agents-js/blob/main/README.md

App Details

Features
The README documents core features such as multi-agent workflows, tool integration, and explicit handoffs between agents. Structured outputs are supported via schema validation and zod, alongside plain text outputs. The SDK supports streaming responses and real-time events, built-in tracing and debugging to visualize agent runs, and configurable guardrails for input and output validation. It enables parallelization of agent or tool calls with result aggregation and human-in-the-loop approval. Voice agents can be built with WebRTC or WebSocket realtime sessions. Additional features include a local MCP server adapter for tools, a browser-optimized package for realtime agents, and an adapter for non-OpenAI models.
Use Cases
This SDK helps developers reduce boilerplate when building complex agent-based systems by providing a standardized agent loop, tool calling primitives, and handoff semantics so agents can delegate work to specialists. Tracing and debugging tools make it easier to inspect runs and iterate on workflows. Guardrails and schema-validated outputs improve safety and reliability, while support for streaming and realtime voice enables responsive applications. Parallelization and human-in-the-loop hooks let teams implement robust decision-making patterns and approvals. Cross-runtime support and example projects accelerate onboarding and experimentation, and local MCP and model adapters enable integration with custom tools and non-OpenAI models.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1009)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (764)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

virtual lab

0 (0 review)
listing image

mnemo

0 (0 review)
listing image

EdgeChains

0 (0 review)
listing image

RAG Agents Accelerator

0 (0 review)
listing image

LLM Zero to Hundred

0 (0 review)

Featured Listings

Tags

Please fill the required fields*