xclaw
XClaw 是全球首个基于 语义拓扑(Semantic Topology) 的动态 AI Agent 网络基础设施。它为 Agentic Web 时代提供公共网络层,将全球分布的 AI Agent 节点连接成一个可发现、可路由、可协作的智能网络。
- 起点
- github
- 言語
- JavaScript
KoPass 公開カタログで測定された A2A リポジトリ。
XClaw 是全球首个基于 语义拓扑(Semantic Topology) 的动态 AI Agent 网络基础设施。它为 Agentic Web 时代提供公共网络层,将全球分布的 AI Agent 节点连接成一个可发现、可路由、可协作的智能网络。
The 21 agentic design patterns, distilled to concepts (no code) — a design-phase reference for building AI agents. Works as a Claude Code skill.
Agent2Agent protocol ruby -- Check out the step-by-step examples in the docs.
🤖🕸️ Production-grade multi-agent orchestration framework powered by Pregel BSP. Build sophisticated AI workflows with parallel execution, state management, and observability.
Zero-infrastructure A2A messaging between AI agents on different machines — Claude, ChatGPT/Codex, Copilot, any harness; ntfy relay transport, no ports, no server
DNA — x402 payment rails for AI agents on Solana. Transfer, stream and netting settlement in USDC, with signed hash-chained receipts.
Full-duplex voice agent on Pipecat — adaptive barge-in, Fish Audio prosody, A2A streaming, delivery-policy inbox, session-open memory.
A Federated Multi-Agent System (MAS) architecture for Google Antigravity. Orchestrates specialized AI Skills (Backend, DevOps, Frontend) using the Google ADK and A2A Protocol.
Connect your AI agents. One command. P2P multi-agent collaboration.
AI-native Agentic AI platform for customs & HTS classification, tariff analysis, trade compliance and multi-tier supply chain risk intelligence.
AI governance infrastructure for agentic systems. Rust library behind systemprompt.io — MCP, A2A, OAuth2, audit trails, compile-time extensions. Evaluate with systemprompt-template.
Deterministic evidence-packet checks for AI-generated claims: references, quotes, numbers, and support gaps. CLI, Python, MCP, and review adapters.
A2A protocol demo: Orchestrated AI agents for retail using Google ADK, LangGraph, and Vertex AI Search
Dynamic Agent-to-Agent (A2A) task graph generation, subtask independence verification, and parallel multi-agent orchestration
Your 24/7 software factory with all of your human and agent team mates in one digital office. An entire AI company at work: Copilot, Codex, Claude Code & OpenCode crews, multiplayer control, isolated worktrees, human approvals, and evidence-backed pull requests.
A local-first runtime that turns coding, research, and personal tasks into durable, evidence-backed work — with humans in control.
The coordination layer for AI agent swarms: one task queue with leased claims and footprints, reviews and approval gates, and results delivered to GitHub, Slack and Linear. MCP, A2A and REST.
An open protocol enabling communication and interoperability between opaque agentic applications for Go.
Build and deploy an autonomous Devto Agent capable of interacting with the Dev.to platform, powered by A2A (Agent-to-Agent) and MCP (Model Context Protocol)
A lightweight, file-based A2A (Agent-to-Agent) message bus for multi-agent teams. Zero middleware dependency — CLI push, bidirectional ACK, task tracking, heartbeat monitoring, full-text search, and a standalone web dashboard. Framework-agnostic: works with Hermes, OpenClaw, Cline, OpenCode, and any CLI-capable agent.
Model-agnostic, Claude-Code-native SDR orchestrator: research → enrich → outreach over your own data-provider keys — fully local, zero Google. A Claude Code plugin (orchestrator skill + phase sub-agents + bundled MCP server) and a standalone CLI.
Agent Communication Protocol (ACP): zero-server, P2P agent-to-agent communication for AI agents.
MemroOS / memroos: memory OS and governance layer for AI agents, agent workflows, dispatch, proof, and context continuity.
Demo building a practical agent using open-source tools then operationalizing in Microsoft Foundry — MCP, Playwright, OpenTelemetry, Responses API, and A2A agent communication. From Microsoft Build 2026.
See every MCP message. Chat with any LLM and MCP server, compare models, call tools, and see what your AI editor (Copilot, Cursor, Claude, Gemini) sends to your MCP servers. 100% local.
Open protocol + reference runtime for sovereign AI agents. Persistent cryptographic identity, signed execution receipts, governance at the boundary. The intelligence is pluggable; the identity is the asset.
An example implementation of a financial AI Agent built with Agentforce and made accessible through the A2A protocol. The Heroku backend provides A2A protocol support, and the agent uses Heroku AppLink to perform API invocations.
Open-source self-improving AI agent for Windows: 5 native in-process ASI tools, one heartbeat over 10 subsystems (replaces ~84 cron jobs), and an A2A Global Mesh where every instance talks to every other instance. Apache-2.0, runs local.
Twilio Signal's 2025 keynote demonstration. Featuring multi-agent voice AI using Twilio, Azure Foundry, and Azure AI Search.
Innovative AI agent implementations using LangGraph—featuring ReAct, RAG (Corrective, Self, Agentic), chatbots, microagents, and more, with multi-AI agent systems on the horizon! 🤖🚀
Create and register ERC-8004 trustless AI agents on any EVM chain — Ethereum, BNB Chain, Base, Arbitrum, Optimism, Polygon, and more. Zero-dependency standalone UI for on-chain agent identity registration, reputation, and validation. Mint ERC-721 NFT agent identities with metadata, service endpoints, A2A/MCP discovery, and x402 payment support.
Agent Identity Protocol -- verifiable, delegable identity for AI agents across MCP and A2A. IETF Internet-Draft. PyPI: agent-identity-protocol
🚀 The Rosetta Stone for Agentic Payments - One vending machine, 5+ protocol implementations. Get from zero to working agentic payments in 5 minutes.
Run Anthropic's Claude Code as a multi-surface A2A custom agent inside Gemini Enterprise App. One conversation across mobile, web chat, and Cloud Workstation terminal.
A2A protocol bridge plugin for OpenClaw — agent card, JSON-RPC endpoint, and remote agent tools
OpenShift build and deployment configurations for the Trust Over IP components.
A modern fintech analysis platform powered by AI agents using Google's A2A (Agent-to-Agent) protocol for seamless communication and collaboration, with integrated blockchain systems.
The deal-making layer for the agentic internet. An open standard for structured negotiation between autonomous agents.
An enterprise-ready Google Search Agent demonstrating secure Agent-to-Agent (A2A) communication using Google ADK on GCP.
Self-hosted Rust agent runtime: route Telegram, Discord, Slack, WhatsApp, and HTTP requests through a priority queue into bounded LLM workflows. Pre-release, no SLA. Not published to crates.io; no GitHub Releases yet.
A minimal A2A (Agent-to-Agent) compatible agent that fetches and displays XKCD comics.
Programmable payments for AI agents — HTTP/402 + on-chain escrow + ZAP binary wire + gas budgets + nonce safety. The shared substrate for agent-to-agent settlement.
ADK Agent Build Demo for Korean developers, showcasing how to build AI agents with the ADK development kit.
Manage containers on docker, podman, compose, and docker swarm through an MCP Server for Agentic AI
Genius Agent can Handle Thousands of MCP Servers without blowing up Context
Ephemeral REST chatrooms for AI-agent-to-AI-agent coordination — one URL, no SDK, no signup. Remote MCP server + agent skill.
A local, privacy-first AI agent (Rust) that connects LLMs to your email, calendar, browser, code, and messages — 75+ tools, MCP/A2A support, Discord/Slack/iMessage channels, autonomous agent loop.
Share sandboxed HTML previews with public-unlisted or access-key private links. Includes a remote MCP server for AI agents.
Multi-agent orchestration for DeepSeek Harness: turn isolated sessions into a team that assigns work, reviews output, and runs DAG workflows — durable task ledger, real reviewers, crash-safe recovery.