Multi-Agent Protocol (MAP) - A protocol for observing, coordinating, and routing messages within multi-agent AI systems
TypeScript SDK for the Multi-Agent Protocol (MAP)
Maps proxy protocols to `http.Agent` implementations
The Agent Client Protocol (ACP) is a protocol that standardizes communication between *code editors* (interactive programs for viewing and editing source code) and *coding agents* (programs that use generative AI to autonomously modify code).
Headless CLI client for the Agent Client Protocol (ACP) — talk to coding agents from the command line
Autonomous AI agent memory system with CLAUDE.md protocol enforcement
A conversational AI-driven telecom multi-agent system for managing call balances, push notifications, marketing, targeting, and sales.
An ACP-compatible coding agent powered by the Claude Agent SDK (TypeScript)
The simplest way to build AI-powered apps
Dual-protocol payment infrastructure for autonomous AI commerce (AP2 + ACP)
Your AI pair programmer
Agents Run API for Inkeep Agent Framework - handles chat, agent execution, and streaming
TypeScript bindings for the LangChain agent streaming protocol
Implementation of the AG-UI protocol for Agno.
The OpenAI Agents SDK is a lightweight yet powerful framework for building multi-agent workflows. This package contains the logic for building realtime voice agents on the server or in the browser.
LangGraph Multi-Agent Supervisor
Docker remote API network layer module.
Shared types and utilities for Rozenite agent packages
Standalone swarm coordination - up to 100+ agents, 4 topologies, hive-mind, consensus
Deco CMS — Self-hostable MCP Gateway for managing AI connections and tools
WebAssembly wrapper for multi-party-schnorr protocol
The OpenAI Agents SDK is a lightweight yet powerful framework for building multi-agent workflows.
Server & Client SDK for Agent2Agent protocol
SOTA NPM module for agentic processes using local or cloud LLMs.
ActiveMatrix is a comprehensive Rails-native Matrix SDK that enables developers to build sophisticated multi-agent bot systems and real-time communication features. This gem provides deep Rails integration with ActiveRecord models, state machines for bot lifecycle management, multi-tiered memory systems, intelligent event routing, connection pooling, and built-in inter-agent communication. Perfect for building chatbots, automation systems, monitoring agents, and collaborative AI systems within Rails applications. Features include command handling, room management, media support, end-to-end encryption capabilities, and extensive protocol support (CS, AS, IS, SS).
An MCP (Model Context Protocol) server that provides browser automation tools for AI agents using Ferrum and headless Chrome. Features 25 tools covering navigation, screenshots, form interaction, JavaScript evaluation, cookies, file downloads, and multi-session management.
Exposes RobotLab robots and networks as A2A agents over HTTP+SSE. Implements the Agent2Agent Protocol v1.0 (Linux Foundation) via the simple_a2a gem. Supports sync and interactive execution modes, bridging RobotLab's AskUser tool to A2A's input_required/resume lifecycle for multi-turn flows without a terminal dependency.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.