Openai agents

An opinionated panel of experts implementation using OpenAI's Assistants API

Cost calculator for Vercel AI SDK token usage. Supports OpenAI, Anthropic, Google, xAI (Grok), and DeepSeek with long context pricing, prompt caching, and reasoning tokens.

Multi-agent orchestration layer for OpenAI Codex CLI

SDK for AI agents, multi-agent rooms, interactive stories, and role-playing games with per-user data isolation and cost tracking

Tutti runtime — multi-agent orchestration for TypeScript

TypeScript SDK for running multi-agent LLM coordination protocols.

Self-hosted TypeScript agent runtime with durable approvals and verifiable run records. Own it, approve it, audit it.

ContextRelay: local multi-agent coding orchestration for Claude Code and Codex

Multi-agent conversation orchestration CLI for AI assistants

AI guardrails and orchestration for Directive. Prompt injection, PII detection, cost tracking, multi-agent patterns.

Local-first AI chat and multi-agent orchestration for Goblintown.

Multi-agent development orchestration platform — 39 specialists, 4-phase workflows, 4 runtime targets (Gemini CLI, Claude Code, OpenAI Codex, Qwen Code)

Hivemind CLI — multi-agent terminal harness (TUI, headless, supervisor).

Munesoft Agent Framework — Build reliable AI agents in minutes. Router brain, verification + auto-repair, session memory, multi-agent orchestration, and first-class integration with the munesoft stack. Zero-dependency core.

AI-powered PR reviewer CLI — local-first, multi-agent semantic analysis

MCP server for bounded multi-agent committee meetings — Codex + Claude Code deliberate in rounds and self-extinguish on <PASS/>

Multi-agent AI code review and decision engine

Type-safe DSL for multi-agent AI workflows — defineAgent, defineWorkflow, loop, sessionToken

Multi-agent orchestration layer for CodeBuddy CLI

🦾 MONSTER ENGINEER v2 - Ultimate AI CLI with 63 Skills, 12 Superpowers, 14 Agents. Multi-Agent Orchestration, Cost-Aware, Security Scorecard, Parallel-First.

Swarm.js - A Node.js SDK for OpenAI multi-agent orchestration

LLM providers, multi-agent routing, CI debugger, and infra diff analysis for DojOps

Universal LLM Command Line Interface with multi-agent support and task management

Multi-Agent AI Orchestration with Git Worktree Isolation for Claude Code

Multi-agent workflow runtime with intelligent routing, guardrails, and observability

A TypeScript AI SDK for building agents, tools, and multi-agent workflows

HalfCopilot — Multi-model Agent Framework CLI

Agent framework for ChatLuna

Tuplet — minimal TypeScript agent framework inspired by Claude Code architecture

Tuplet — minimal TypeScript agent framework inspired by Claude Code architecture

Production-grade agent framework with structured context management, compaction, tools, and MCP support

The explainable agent framework — backtrack a wrong answer to the exact context that caused it (evidence, not guesses). Built on footprintjs.

A JavaScript-based ReAct (Reasoning + Acting) AI agent framework using OpenAI API

A lightweight, elegant, and feature-complete TypeScript AI Agent framework

LobeHub - an open-source,comprehensive AI Agent framework that supports speech synthesis, multimodal, and extensible Function Call plugin system. Supports one-click free deployment of your private ChatGPT/LLM web application.

A TypeScript agent framework for Node.js, React, Vue, and OpenAI-compatible models.

Node.js binding for Ambi — a high-perf, cross-platform AI Agent framework built in Rust

A minimal, extensible TypeScript Agent framework

Maiar: A Composable, Plugin-Based AI Agent Framework

Programmatic SDK for building AI agents with Robota — provides InteractiveSession, createQuery(), command APIs, permissions, hooks, and context loading

Headless agent framework for claude-code-kit — LLM query loop, tool execution, multi-provider

AI Agent Framework for building intelligent agents with LLM integration, function calling, and reflection capabilities

Simple and easy agent framework, include various of structured data manipulation, agent and function compositing, code editing, fs and more!

Node.js binding for Ambi — a high-perf, cross-platform AI Agent framework built in Rust

Node.js binding for Ambi — a high-perf, cross-platform AI Agent framework built in Rust

Node.js binding for Ambi — a high-perf, cross-platform AI Agent framework built in Rust

A lightweight, decoupled AI agent framework with built-in debugger

Node.js binding for Ambi — a high-perf, cross-platform AI Agent framework built in Rust

Agent framework for building AI-powered applications with support for OpenAI, tool usage, and persistent storage

Production-grade AI agent framework — the Next.js for AI agents

A simple and powerful Typescript based agent framework to help businesses thrive in the AI Agent revolution.

A platform-agnostic AI agent framework for building autonomous AI agents with tool execution capabilities

A platform-agnostic AI agent framework for building autonomous AI agents with tool execution capabilities

FormAgent SDK - AI Agent framework with streaming support, tool execution, skill management, and hooks system

A lightweight, extensible AI Agent framework with tool calling, MCP integration, and streaming support

TypeScript-based AI agent framework with native LLM integration, workflows, and 15+ built-in integrations (Development Preview)

OpenAI provider for the Fraimwork AI agent framework.

Type-safe AI agent framework for Igniter.js with MCP integration, custom toolsets, and memory system

SYMindX - AI Agent Framework CLI with NyX agent

A lightweight, extensible AI Agent framework with tool calling, MCP integration, and streaming support

TypeScript AI Agent framework - from single agent to multi-agent cluster orchestration

🧠 Generic Multi-Provider AI Agent Framework - No SDK dependencies, Raw HTTP only

A lightweight, extensible AI Agent framework built with Node.js and TypeScript

A headless AI agent framework with CLI, SDK, and server adapters — skills, multi-provider LLM support, and Docker-native deployment.

A modular AI agent framework with multi-LLM support, tool execution, browser/desktop control, Feishu/QQ integration, and self-evolving skills

agentlib core runtime engine — type-safe, extensible AI agent framework for Node.js

🌟 The Revolutionary 5-Minute AI Agent Framework for TypeScript/JavaScript - Build production agents 10x faster!

AI agent framework with multi-phase orchestration, tool execution, and provider adapters

Microsoft AutoGen multi-agent framework configuration generator CLI

Agentic - Production-ready AI agent framework with stateless architecture and multi-LLM support

Enterprise-grade AI Agent Framework - DDD Architecture, Microkernel, ReAct Thinking, Multi-LLM Support, MCP Protocol, Secure Sandbox

AI agent framework with defense-in-depth security, multi-agent orchestration, and provider abstraction

Delphi is a versatile and adaptable conversational agent framework that streamlines the creation and management of chatbots and AI-driven communication systems.

Multi-provider AI agent framework for Model Context Protocol (MCP) servers

Agentic AI utils which work with any LLM and TypeScript AI SDK.

Agentic AI Library specialized in LLM Function Calling

OpenAI (and OpenAI-compatible) adapter for agentic-kit

Agentic AI Library specialized in LLM Function Calling

Open-source merchant facilitator for the Agentic Commerce Protocol (ACP) bridging ChatGPT, Claude, Gemini, and other agentic-commerce clients to MercadoLibre and MercadoPago. ACP-compliant checkout sessions, signed webhooks, /.well-known/acp.json discover

V3 Embedding Service - OpenAI, Transformers.js, Agentic-Flow (ONNX), Mock providers with hyperbolic embeddings, normalization, and chunking

harmony-agentic-decisions. Production-grade human-in-the-loop decision workflows with LLMs and messaging channels.

Agentic toolset for building applications using arvo-core and arvo-event-handler

Agentic AI Library specialized in LLM Function Calling

Agentic chat example using AG-Kit Agents

Agentic AI Library specialized in LLM Function Calling

AI agent debugging, collaboration, and trace observability. Built for teams using CrewAI, OpenAI, and more.

CrewAI bridge for SwarmSync.AI — OpenAI function definitions, REST executor, and Python bridge snippet for using SwarmSync as CrewAI tools.

Seracade is a drop-in OpenAI-compatible routing proxy for AI agent teams. Six named capabilities: Call (every request, addressable and replayable), Step (sub-Call routing context inside agent trajectories), Quality Score (calibrated, version-stamped quali

AxonFlow SDK - Add invisible AI governance to your applications in 3 lines of code

Drop-in Tessera integration for the Vercel AI SDK. One line of config routes generateText / streamText / generateObject / streamObject through Tessera's auto-route + auto-cache + auto-compress + auto-batch proxy. Compatible with @ai-sdk/openai, @ai-sdk/an

Stealth browser for AI agents. Bypasses Cloudflare, DataDome, PerimeterX. Residential IPs from 10+ countries. iPhone 15 Pro fingerprint. Drop-in Playwright replacement — launchHuman() just works.

Drop-in Tessera integration for the Mastra agent framework. One line of config routes every Mastra Agent's LLM calls through Tessera's auto-route + auto-cache + auto-compress + auto-batch proxy. Compatible with @ai-sdk/openai, @ai-sdk/anthropic, @ai-sdk/m

A node package for building AI agents

Universal AI agent packaging format — bundle souls, memories, skills, tools, crons, subagents, and encrypted secrets into a single portable archive, then compile to any platform.

Enterprise AI agent governance framework. Hook-based enforcement, compliance packs (SOC 2, HIPAA, GDPR, PCI DSS, DORA, EU AI Act, ISO 27001), audit trails, multi-LLM adapter architecture (Claude production today; additional providers on roadmap).

A2A (Agent-to-Agent) protocol wrapper for the GitHub Copilot SDK. Drop a JSON config file in, get a fully-spec-compliant A2A server out. Supports any agent persona, MCP tool servers, streaming, context building, and multi-turn conversations.

Three hooks that wire an AI copilot into your React app's state, actions, and forms. AI SDK 6 native. Ships with an optional .pilot/ skills folder and an `agentickit` CLI for scaffolding it. MIT.

An MCP server written in Go that provides FHIR R4-compliant API access to EMR systems like Epic, Cerner, and Google Cloud Healthcare API

Universal AI Agent SDK for TypeScript — multi-model support with built-in tools, powered by any LLM.

Universal AI Agent SDK for TypeScript — multi-model support with built-in tools, powered by any LLM.