Awesome AI AgentsCommunication Protocols

google-agentic-commerce/AP2

⭐ 3177 Python added to this list on 2025-10-04 repository created 2025-05-30

The Agent Payments Protocol (AP2) project by google-agentic-commerce is focused on building a secure and interoperable future for AI-driven payments. This repository contains code samples and demos that showcase the Agent Payments Protocol, which facilitates interactions between agents and payment systems in a secure and standardized manner. The project aims to enable seamless and trustworthy AI-driven commerce by providing a protocol that supports various agents and servers. The repository includes curated scenarios demonstrating key components of the protocol, with implementations available in both Python and Android environments. These scenarios are designed to illustrate how agents can interact with payment systems and assist in shopping experiences. The samples utilize the Agent Development Kit (ADK) and Gemini 2.5 Flash, although the protocol itself is not dependent on these tools, allowing developers the flexibility to use their preferred technologies. The project provides detailed setup instructions, including prerequisites such as Python 3.10 or higher and the 'uv' package manager. It supports authentication via Google API Key for development and Vertex AI for production environments, ensuring secure access to Google services. The repository also includes scripts to simplify running scenarios locally, making it easier for developers to test and experiment with the protocol. Additionally, the core protocol objects are defined in the 'src/ap2/types' directory, with plans to publish a PyPI package for easier integration in the future. Overall, AP2 represents a significant step towards enabling AI-driven payments with a focus on security, interoperability, and developer accessibility, making it a valuable resource for those interested in the future of AI commerce and payment technologies.

https://github.com/google-agentic-commerce/AP2

a2aadkagent-development-kitagent-payments-protocolagentic-aiagentsai-commerceai-driven-paymentsandroid-scenariosap2code-samplesdemosgemini-2.5-flashgen-aigenerative-aigoogle-api-keyinteroperable-paymentspayment-protocolpaymentsprotocol-objectspypi-packagepython-scenariossecure-authenticationsecure-paymentsshopping-assistantvertex-ai

Also in Communication Protocols

novuhq/novu

Novu is an open-source communication infrastructure that unifies notification delivery across various channels for both products and AI agents, offering a single API for multi-channel messaging, wo...

a2aproject/a2a-samples

Official sample repository for the Agent2Agent (A2A) protocol, with runnable agent and host implementations in Python, Go, Java, JavaScript and C# built on the official A2A SDKs.

agent-network-protocol/AgentNetworkProtocol

AgentNetworkProtocol (ANP) is an open-source protocol designed to enable secure, decentralized, and efficient communication and collaboration among intelligent agents, aiming to become the HTTP of the Agentic Web era.

universal-tool-calling-protocol/python-utcp

Python reference implementation of the Universal Tool Calling Protocol, a plugin-based standard that lets agents discover and call existing tools directly over HTTP, SSE, CLI and other transports.

google-agentic-commerce/a2a-x402

Specification and reference libraries for the x402 extension to the Agent-to-Agent protocol, letting one agent charge another for a service through on-chain stablecoin payments in a three-message flow.

a2aproject/a2a-java

a2a-java is the official Java SDK for the Agent2Agent protocol, providing client and server modules that expose agentic Java applications over JSON-RPC, gRPC and REST transports.

a2aproject/a2a-go

Go SDK for the Agent2Agent (A2A) protocol that provides client and server libraries for exposing and consuming agents over gRPC, REST and JSON-RPC, together with a CLI for discovery and messaging.

thu-nics/C2C

Research implementation of Cache-to-Cache, a method that lets two large language models exchange semantics directly by projecting and fusing their KV-caches instead of passing generated text between them.