diff --git a/README.md b/README.md index b69c0dc..61b564f 100644 --- a/README.md +++ b/README.md @@ -379,15 +379,15 @@ This section aims to list standalone tools and utilities related to the A2A prot * ⚙️ [Handler](https://github.com/alDuncanson/Handler) by [@alDuncanson](https://github.com/alDuncanson) [![Stars](https://img.shields.io/github/stars/alDuncanson/Handler?style=social)](https://github.com/alDuncanson/Handler) - A2A Protocol client and developer toolkit featuring an interactive TUI, CLI commands, MCP server integration, agent card inspection, and a bundled reference agent. * ⚙️ [a2a-editor](https://github.com/open-resource-discovery/a2a-editor) by [@open-resource-discovery](https://github.com/open-resource-discovery) [![Stars](https://img.shields.io/github/stars/open-resource-discovery/a2a-editor?style=social)](https://github.com/open-resource-discovery/a2a-editor) - UI components for editing, viewing, and testing A2A agent cards and interactions, with installable packages and self-hosted local or Docker usage. * ⚙️ [A2A MCP Server](https://github.com/GongRzhe/A2A-MCP-Server) by [@GongRzhe](https://github.com/GongRzhe) [![Stars](https://img.shields.io/github/stars/GongRzhe/A2A-MCP-Server?style=social)](https://github.com/GongRzhe/A2A-MCP-Server) - Bridge server connecting MCP-compatible AI assistants (like Claude) with A2A agents, enabling seamless cross-protocol discovery, registration, and task management. Supports stdio, streamable-http, and SSE transports. - * ⚙️ [AI-Mocks](https://github.com/mokksy/ai-mocks) by [@mokksy](https://github.com/mokksy) [![Stars](https://img.shields.io/github/stars/mokksy/ai-mocks?style=social)](https://github.com/mokksy/ai-mocks) - Kotlin/JVM mock-server toolkit (built on Ktor) for testing A2A integrations. Ships a dedicated `ai-mocks-a2a` module with a `MockAgentServer`, full A2A protocol coverage (11 endpoints), real Server-Sent Events streaming, plus shared mocks for OpenAI/Anthropic/Gemini/Ollama — useful for service virtualization, contract tests, and offline development. MIT licensed and published on Maven Central. - * ⚙️ [a2a-ui](https://github.com/a2anet/a2a-ui) by [@a2anet](https://github.com/a2anet) [![Stars](https://img.shields.io/github/stars/a2anet/a2a-ui?style=social)](https://github.com/a2anet/a2a-ui) - A general-purpose web UI for the Agent2Agent (A2A) Protocol built with React, Next.js, and Material UI on top of the official `a2a-js` SDK. Add any A2A-compatible agent by URL, fetch its AgentCard, run multi-turn chat sessions with `Context` and `Tasks`, render markdown-supported `Messages`/`Artifacts`, and visualize streaming responses and tool-call traces — effectively an early "web browser" for A2A agents. Apache 2.0. - * ⚙️ [a2a-ui](https://github.com/a2a-community/a2a-ui) by [@a2a-community](https://github.com/a2a-community) [![Stars](https://img.shields.io/github/stars/a2a-community/a2a-ui?style=social)](https://github.com/a2a-community/a2a-ui) - Modern, production-ready web UI for Google A2A built with Next.js, TypeScript, Tailwind CSS, and shadcn/ui. Features agent CRUD and configuration, Telegram-style real-time chat with streaming, Phoenix/Jaeger trace visualization, dark/light/system themes, Docker and Vercel deployment. MIT licensed. + * ⚙️ [AI-Mocks](https://github.com/mokksy/ai-mocks) by [@mokksy](https://github.com/mokksy) [![Stars](https://img.shields.io/github/stars/mokksy/ai-mocks?style=social)](https://github.com/mokksy/ai-mocks) - Kotlin/JVM mock-server toolkit (built on Ktor) for testing A2A integrations. Ships a dedicated `ai-mocks-a2a` module with a `MockAgentServer`, full A2A protocol coverage (11 endpoints), real Server-Sent Events streaming, plus shared mocks for OpenAI/Anthropic/Gemini/Ollama — useful for service virtualization, contract tests, and offline development. MIT licensed and published on Maven Central. * ⚙️ [a2a-ui](https://github.com/a2a-community/a2a-ui) by [@a2a-community](https://github.com/a2a-community) [![Stars](https://img.shields.io/github/stars/a2a-community/a2a-ui?style=social)](https://github.com/a2a-community/a2a-ui) - Modern, production-ready web UI for Google A2A built with Next.js, TypeScript, Tailwind CSS, and shadcn/ui. Features agent CRUD and configuration, Telegram-style real-time chat with streaming, Phoenix/Jaeger trace visualization, dark/light/system themes, Docker and Vercel deployment. MIT licensed. + * ⚙️ [inference-gateway/cli](https://github.com/inference-gateway/cli) by [@inference-gateway](https://github.com/inference-gateway) - A CLI tool for the Inference Gateway — manage and route AI inference requests with A2A protocol support. Built in Go, this agentic command-line assistant can write code, understand project context, and use tools to perform real tasks while natively supporting the Agent2Agent protocol for interoperable agent communication. * ⚙️ [dify-a2a-plugin](https://github.com/flyryan/dify-a2a-plugin) by [@flyryan](https://github.com/flyryan) [![Stars](https://img.shields.io/github/stars/flyryan/dify-a2a-plugin?style=social)](https://github.com/flyryan/dify-a2a-plugin) - A2A protocol plugin for Dify that enables cross-agent communication. Connects Dify workflows to external A2A-compatible agents via JSON-RPC 2.0 with synchronous and asynchronous modes, SSE streaming, and Bearer/API Key/Basic auth. Supports A2A v0.3.0. Apache 2.0. * ⚙️ [a2a-bridge](https://github.com/firstintent/a2a-bridge) by [@firstintent](https://github.com/firstintent) [![Stars](https://img.shields.io/github/stars/firstintent/a2a-bridge?style=social)](https://github.com/firstintent/a2a-bridge) - Agent-to-agent bridge that lets Claude Code, Codex, OpenClaw, Hermes Agent, Gemini CLI, Zed, and VS Code agents talk to each other through one daemon. Translates between A2A (HTTP + SSE), ACP (stdio JSON-RPC), and MCP channels with multi-session isolation and an SQLite task log. MIT licensed. * ⚙️ [a2a-gateway](https://github.com/eliasecchig/a2a-gateway) by [@eliasecchig](https://github.com/eliasecchig) [![Stars](https://img.shields.io/github/stars/eliasecchig/a2a-gateway?style=social)](https://github.com/eliasecchig/a2a-gateway) - Multi-channel gateway that connects any A2A agent to Telegram, Slack, WhatsApp, Google Chat, Email, Discord, and custom channels. Handles message chunking, rate limiting, retries, streaming responses, and per-channel markdown formatting; supports single-user and multitenant deployment. Apache 2.0. * ⚙️ [hermes-a2a-bridge](https://github.com/asimons81/hermes-a2a-bridge) by [@asimons81](https://github.com/asimons81) [![Stars](https://img.shields.io/github/stars/asimons81/hermes-a2a-bridge?style=social)](https://github.com/asimons81/hermes-a2a-bridge) - Local-first bridge adding A2A protocol support to Hermes Agent. Supports agent discovery, task send/stream/manage, SSE streaming, SQLite persistence, gated file staging, and bearer auth. MIT licensed. * ⚙️ [Engram](https://github.com/kwstx/translator) by [@kwstx](https://github.com/kwstx) [![Stars](https://img.shields.io/github/stars/kwstx/translator?style=social)](https://github.com/kwstx/translator) - The adaptive semantic interoperability layer for AI agents. Translates and routes across protocols, auto-generates schemas, handles schema drift, and supports cross-protocol federation (MCP, CLI, A2A, ACP) with multi-hop handoffs. MIT licensed. -* ⚙️ [Swival](https://github.com/Swival/swival) by [@Swival](https://github.com/Swival) [![Stars](https://img.shields.io/github/stars/Swival/swival?style=social)](https://github.com/Swival/swival) - A small, open-source CLI coding agent that exposes itself as an A2A endpoint (`swival --serve`) and can call remote A2A agents. Features multi-turn context, SSE streaming, rate limiting, bearer auth, MCP support, cross-session memory, and built-in security auditing. MIT licensed. + * ⚙️ [Swival](https://github.com/Swival/swival) by [@Swival](https://github.com/Swival) [![Stars](https://img.shields.io/github/stars/Swival/swival?style=social)](https://github.com/Swival/swival) - A small, open-source CLI coding agent that exposes itself as an A2A endpoint (`swival --serve`) and can call remote A2A agents. Features multi-turn context, SSE streaming, rate limiting, bearer auth, MCP support, cross-session memory, and built-in security auditing. MIT licensed. + ## 📚 Tutorials & Articles