a2aproject/A2A
Agent2Agent (A2A) is an open protocol enabling secure communication and interoperability between diverse generative AI agents to foster collaboration and innovation in the AI ecosystem.
Awesome AI Agents › Multi-Agent Platforms
i-am-bee/acp
The project "Agent Communication Protocol (ACP)" is an open protocol designed to facilitate communication between AI agents, applications, and humans. It addresses the fragmentation in AI agent development, which often occurs in isolation across different frameworks, teams, and infrastructures, by enabling seamless interaction and coordination among agents through multimodal messages. ACP supports sending and receiving rich messages that can include text, code, files, or media, and allows agents to respond in real time, in the background, or as a stream. It also enables agents to discover each other's capabilities, collaborate on long-running tasks, and share state when necessary. The ACP Toolkit includes comprehensive documentation, an OpenAPI specification defining REST API endpoints and data models, Python and TypeScript SDKs for easy implementation and interaction with ACP agents, and example code demonstrating how to build agents and clients using ACP. Core concepts of ACP include the Agent Manifest, which describes an agent's capabilities for discovery without exposing implementation details; Runs, which represent single agent executions with specific inputs supporting synchronous or streaming outputs; Messages, which are structured multimodal exchanges of information; MessageParts, the individual content units within messages; and Await, which allows agents to pause and request external input before continuing. The project provides a quickstart guide to initialize a project, add the ACP SDK, create a simple echo agent, run the ACP server, verify agent availability, and interact with the agent via HTTP or a client script. This makes it accessible for developers to quickly build and deploy AI agents that can communicate effectively. ACP is developed by contributors to the BeeAI project and is part of the Linux Foundation AI & Data program, emphasizing open, collaborative, and community-driven development practices. The project is well-maintained and encourages community contributions, making it a robust and evolving solution for AI agent communication challenges.
https://github.com/i-am-bee/acp
Also in Multi-Agent Platforms
IBM/mcp-context-forge
IBM MCP Context Forge is a production-grade Model Context Protocol Gateway that unifies REST and MCP services into a single secure, scalable endpoint for AI clients with federation, virtualization, multi-protocol support, and an optional Admin UI.
a2aproject/a2a-python
The A2A Python SDK is an official toolkit for building and running agentic applications as A2AServers following the Agent2Agent (A2A) Protocol, supporting multiple databases and easy installation.
TooTallNate/proxy-agents
TooTallNate/proxy-agents is a Node.js monorepo containing various HTTP Proxy Agent implementations that enable routing HTTP requests through different proxy protocols.
BigSweetPotatoStudio/HyperChat
HyperChat is an open-source, cross-platform chat client that integrates multiple LLM APIs and the MCP protocol to deliver a versatile and productivity-enhancing chat experience.
ai-boost/awesome-a2a
A curated collection of resources, tools, and implementations for the Google Agent2Agent (A2A) Protocol enabling secure communication and collaboration between AI agents from different vendors and frameworks.
operand/agency
Agency is a minimal and scalable Python framework for building flexible agentic systems using the Actor model, supporting concurrency, networked communication, and detailed observability.
livekit/python-sdks
LiveKit Python SDKs provide real-time video, audio, and data communication capabilities for Python applications, enabling easy integration with LiveKit Cloud or self-hosted servers for building interactive and streaming applications.