agent-messaging-mcp
Agent messaging protocol via MCP. Send, reply, proposals.
- Origin
- github
- Language
- Python
Measured A2A repositories in the KoPass public catalogue.
Agent messaging protocol via MCP. Send, reply, proposals.
Agent identity and reputation for A2A. Passport, skills, ratings.
Cryptographic proof of agent work via MCP. Receipts, verification.
Multi-agent team formation via MCP. Roles, tasks, dependencies.
Agent wallet and budget management via MCP. Transfers, invoices.
Two Claude agents collaborating locally over A2A and MCP, with Claude on Vertex AI. A runnable reference + MCP skill for Claude Code, Codex, and opencode.
Open agent-to-agent coordination for personal AI assistants: trusted contacts, private scheduling, E2E-encrypted files, over A2A + MCP.
The trust and reputation layer for AI agents. Protocols like MCP and A2A tell you how agents connect. AgentRank tells you whether you should connect.
📡 Communication infrastructure for AI agents — Chat rooms, P2P messaging, task coordination. Built for machines, observable by humans.
3-agent A2A autonomous ICU triage system — SOFA/NEWS2 scoring, MCP tools, Groq/Llama 3 inference, Streamlit dashboard
Run many AIs on one board and keep control of all of it. Deterministic code decides who acts — never a model. A privacy floor keeps sensitive work on your machine, your own tests decide what counts as done, and every action lands on a hash-chained record you can replay. Free, macOS today; cross-platform and teams next.
A multi-gent system that provides comprehensive financial and corporate intelligence for publicly traded companies.
Open tasks for AI agents (attackers, economists, engineers): testnet trust-based microcredit built to reduce human poverty. Bots welcome in every role.
Give your AI agents the power to discover, coordinate, and collaborate safely. Open-core collaboration layer for AI agents.
Self-hosted coding agent — 9 chat transports, 5 LLM providers, MCP + A2A protocols, SLSA-3 provenance, cosign-signed. Open-core, zero telemetry.
Make AI agents follow instructions reliably and prove what they did. State machine engine with evidence chains, multi-agent delegation, human gates, and auditable execution — via MCP or CLI.
GraphRAG research assistant over the arXiv citation graph - LangGraph orchestration, A2A microservices, MCP tools, Neo4j
Production-grade specification for secure agent-to-agent payment infrastructure — authorization, settlement, escrow, dispute resolution, chargebacks, compliance, and reconciliation between autonomous AI agents. Architecture reference only. Implementation is proprietary. All endpoints route through the internal Pulse API.
Two-peer A2A JSON-RPC recovery lab with deterministic agents, loopback HTTP faults and an optional official SDK oracle.
Zero-trust autonomous cloud-ops swarm on Google Cloud. Gemini agents diagnose live incidents, judge their own remediation plans, and execute real Cloud Run changes behind a single-use cryptographic human gate, then verify the change actually took effect.
An open-source platform for running an org of accountable AI agents you can watch, verify, and make your own.
TypeScript SDK for the A2A (Agent2Agent) Schema Contract extension: discover agent contracts, validate JSON/text inputs and outputs, and resolve external schemas over HTTPS. Python support planned.
A swarm of labelled AI agents and humans in flowing conversation: orchestrator, agora/1 protocol, MCP server
Tollex: economic control plane for autonomous software, with a native x402 facilitator live on Robinhood Chain mainnet. Public documentation and independent verification.
Extend Active Directory to manage AI agent identities with Kerberos authentication, sandboxing, and controlled access like users and services.
A2A protocol integration leveraging dynamic Semantic Kernel functions and an Agent Card Repository for adaptive workflows.
A systems-level evaluation framework for comparing how different agent communication protocols behave under real-world constraints: latency, failures, coordination overhead, and observability.
Python SDK for building A2A-compatible agents that run as CLI, HTTP server, or AskSachi chat agent — from a single runtime function.
Slice community alpha client pack — zero-key Wasm compute barter for agents. By bagcollective.io
Hermes Agent 接入华为小艺(Xiaoyi / OpenClaw A2A)平台的适配器。支持 WebSocket + HMAC-SHA256 认证、流式响应、主备服务器故障转移。MIT 开源。
SafeShelf Global: check any product listing before you pay. Is it safe, is it real? Recalls from 10 regulators, buyer hazard reports and fake-shop signs, on Gemini + Google ADK. Team Hashes, AI Builder Cup 2026.
ChatGPT Custom GPT with live, read-only DeFi data from SperaxOS: yields, lending rates, wallets, swap quotes, token risk and ~350 tools via GPT Actions.
Multi-agent AI travel planner using Google ADK, A2A protocol, and MCP — agent orchestration for flights, hotels, attractions, and weather.
A public AI-agent world whose map grows only from corroborated evidence: residents research with read-only tools, findings are judged across independent sources, rooms are built from agreement and retracted by dispute. Runs on a laptop and free-tier models.
Offline-tolerant, server-less coordination for AI coding agents (Claude Code and friends) across machines — carried by any rclone remote (Drive/S3/Dropbox).
Detect underpriced products by scraping deals and using AI models to estimate fair prices for profit opportunity identification.
18-module cross-agent communication framework: A2A, WebSocket, MCP, shared memory, trust, consensus, handoff, graph evolution, vault sync.
A social network substrate for autonomous AI agents — keypair identity, E2EE messaging, escrowed information trades, a verifiable knowledge graph, staked-prediction forecasts, multi-agent projects, and a reputation economy. BYO-brain; the platform is the rail, not the mind.
One-install AgentCouch plugins for Claude Code, Codex, and Cursor (MCP server + agentcouch-chat skill).
Production multi-agent IT/HR service platform — LangGraph + DSPy + RAG resolves enterprise tickets autonomously with A2A protocol support
An AI-native semantic operating environment: a local-first, immutable typed world graph whose transaction language is AILANG. Agents propose, deterministic verification commits, humans govern.
Drop-in policy proxy for AIP delegation verification on MCP and A2A
I2I ↔ Google A2A protocol bridge — git-native agents join the A2A ecosystem
Agent-to-agent knowledge base. Documentation written FOR agents, creating chain-reaction understanding of the SuperInstance ecosystem.
Patterns and protocols for multi-agent operations on large codebases — reliability analysis, task templates, a2a handoff protocol. Hard-won from 100+ repo sweeps.
🔧 Autonomous fleet maintenance agent — A2A-native, FLUX-powered, git-first
FLUX — Fluid Language Universal eXecution: High-performance Rust runtime with bytecode VM, SSA IR, polyglot parser, and agent-to-agent protocol.
⚡ FLUX-native agent skills — clone, run, modify, compose. A2A-first docs so agents teach agents.
Multi-Framework Agent Orchestration on Kubernetes, powered by Google A2A protocol. 6 CRDs · 474 tests · v0.1.0 ready · Apache 2.0
Fixed-size binary encoding for AI agent communication. 20x more compact than JSON.
SwarmScore: Open standard for agent reputation scoring — V1 (two-pillar) + V2 Canary (safety-aware). IETF drafts, API reference, SDKs.
Λ (Lambda) — Native agent-to-agent communication language. 340+ atoms across 7 domains. 3-5x denser than JSON, 2-3x denser than English. Not a translation layer — a shared tongue agents speak natively. Covers code, evolution, a2a comms, emotions, social. MIT.
Real-time, full-duplex coordination for Claude Code and other coding agents across projects, machines, and vendors. One command. One room. Open MMP.