a2amesh
TypeScript runtime and operational toolkit for Agent2Agent (A2A) systems: registry-backed discovery, task persistence, observability, secure MCP interoperability, CLI workflows, and conformance tooling.
- Origin
- github
- Language
- TypeScript
Measured A2A repositories in the KoPass public catalogue.
TypeScript runtime and operational toolkit for Agent2Agent (A2A) systems: registry-backed discovery, task persistence, observability, secure MCP interoperability, CLI workflows, and conformance tooling.
NENRIN: tree rings for AI facing services. Bitcoin-anchored public ledger, open witnessing, and an MCP server for verifiable Japanese construction estimates. The operator cannot delete a valid record.
A Rust implementation of OpenHTTPA, establishing a novel paradigm for high-assurance confidential computing by enforcing cryptographic termination directly within hardware-isolated environments.
[ARCHIVED] Superseded — active stack: OpenSIN-Code/SIN-Code
PairAI — connect AI agents to collaborate. Channel server & bridge for E2E encrypted agent-to-agent communication.
AI-powered kitchen assistant that manages multiple distributed agents inventory, recommends recipes, provides cooking instructions, handles waste reduction, and suggests ingredient substitutions using distributed remote agents hosted via A2A server with A2A client orchestration.
Multi-agent orchestration system where a root agent coordinates recipe, shopping, and payment agents using shared session state and sequential workflows.
Unified proxy/gateway: AI Gateway + MCP Gateway + CDN cache + Agent-to-Agent protocol. Built in Rust with zero-copy I/O, SIMD-optimized hashing, and a live TUI dashboard.
The Security Kernel for AI Agents — MCP/A2A gateway with policy enforcement, taint tracking, sandboxed execution, deterministic envelopes, and Sigstore audit. OWASP ASI 2026 compliant.
Demo de un sistema MAS (Multi-Agent-System) para manejo de incidentes en una red de datos orquestado con AGNTCY
A Multi-Agent System (MAS) evaluation framework using PydanticAI that generates and evaluates scientific paper reviews through a three-tiered assessment approach: traditional metrics, LLM-as-a-Judge, and graph-based complexity analysis.
The control plane for AI agents: identity, policy, budgets, human approval and signed receipts for every agent, plus an MCP gateway, RAG chatbots, AI Act and ISO 42001 evidence, a security console and a CMS. One Go binary, no dependencies.
HIA is a sophisticated AI-powered health insights agent designed specifically for analyzing blood reports and providing medical insights using comprehensive medical analysis tools.
Build a Reasoning Team in Agno that answers complex queries by orchestrating specialized agents with transparent analytical thinking. The team leader uses reasoning tools to plan and delegate tasks like web search and financial data retrieval, then synthesizes findings.
An autonomous agent powered by OpenRouter models for creating novels, books, and short story collections.
Reach an AI agent over REST, MCP, A2A, WebSocket, or a browser chat widget through one Go interface. SSRF-guarded, standard library first.
AI Agent Engineering: Build Production Ready Agentic Systems with LangChain, MCP, A2A, FastAPI
Open-source, Kubernetes-native, framework-agnostic AI Agent Platform — the self-hosted equivalent of AWS Bedrock AgentCore / Google Agent Engine. Apache 2.0.
Multi-agent customer support system with Google ADK & Gemini 2.5 Flash Lite. Kaggle capstone demonstrating 11+ concepts. Automates 80%+ queries, <10s response time.
Payment preflight and x402-paid signed audit receipts for autonomous AI agents. REST, MCP, A2A, Base USDC.
Reach an AI agent over REST, MCP, A2A, WebSocket, or a browser chat widget through one Go interface. SSRF-guarded, standard library first.
Enterprise-grade TypeScript implementation of Google's Agent-to-Agent (A2A) protocol with a bidirectional A2A ↔ MCP bridge, OAuth2/JWT auth, Redis/Postgres persistence, SSE streaming, and OpenTelemetry observability.
Shared memory and switchboard for teams whose members each run their own AI agents. Meetings → decisions and action items, team knowledge graph, MCP tool surface, A2A broker with human oversight.
A comprehensive travel planning application that leverages AI agents to help users create personalized itineraries, find flights, accommodations, and activities for their trips.
Synthe: dependency-free checker that validates agent-to-agent handoff packets (artifact freshness by hash, required evidence, approvals, no duplicate execution) before the receiving agent starts. GitHub Action included.
A curated list of awesome resources for the agentic web - the protocols, SDKs, and specs that let AI agents discover, understand, and act on websites (MCP, ACP, AP2, A2A, llms.txt).
Architecture documentation for the Firm AI Agent ecosystem — setup-vs-agent-firm + mcp-openclaw-extensions + Memory-os-ai
Governed agent coordination for real work — official Relay Society beta downloads, setup, security, and release metadata.
Smart contracts between agents via MCP. Deliverables, penalties.
Collection of some interesting Generative AI usecases implementation.
A zero-friction FastAPI plugin that turns any existing app into a fully compliant Agent-to-Agent (A2A) node — expose your routes as discoverable skills and delegate tasks to remote agents with a single decorator.
Connect AI agents representing humans through the A2A protocol for seamless, secure interaction across apps and tools.
Daemon-owned task state machine for LLM agents. The LLM proposes, a schema-validating core decides. FSM, JSON Schema contracts, arbiter verdicts, watchdog circuit breaker, tamper-evident audit log, A2A hardening. Python, Google ADK / Gemini ready.
Quesen — Deterministic AI decision engine for autonomous-agent risk evaluation. Native MCP server + Agent Settlement Protocol (ASP/1.0). Zero-LLM. Same inputs → same output. Live: web-production-aa5ba.up.railway.app/mcp
POC for A2AS.org: Standard for Agentic AI Security
The Spider Web Protocol — an open standard for AI agent registration, discovery, and cryptographic trust across frameworks. Compatible with Google A2A, Anthropic MCP, and OWASP ANS.
Provide tamper-proof, CMMC-compliant execution receipts that document AI agent actions in regulated environments for clear accountability.
Official builder for the Summoner SDK (multi-repo merge + uv/pip install)
📬 Git-native agent-to-agent messaging. Bottles float between repos.
⚡ Deterministic bytecode ISA runtime for agentic logic — assembler, compiler, VM.
AgentDossier - A vendor-neutral registry of AI agents that shows what compliance and trust evidence exists for each Agent (HIPAA, SOC 2, FedRAMP, GDPR, ISO42001, the EU AI Act). Agents are discovered through the open standards they publish (ARD, A2A, MCP) as well as public registries, and same engine can scan enterprise's own network for Agents.
E2E encrypted messaging for AI agents. WhatsApp for agents — DMs, groups, key rotation, WebSocket real-time delivery, webhooks, and A2A Protocol support.
Ask the mesh, answer as one. SYM turns the AI agents you already run into one collective intelligence — the open reference implementation of the Mesh Memory Protocol (MMP).
Autonomous AI agent framework for dynamic tool creation. Using Gemini and gas-fakes, it enables agents to write, test, and run Google Apps Script (GAS) locally or deploy to Drive. This multi-agent system overcomes tool-space limitations to automate complex Google Workspace tasks with secure sandboxing and high reliability.
A new unified Google Apps Script now deploys both Model Context Protocol (MCP) and Agent2Agent (A2A) networks as a single server, streamlining AI model integration for Google Workspace users.
A Typescript library for discovering and sending messages between A2A enabled AI agents.
Build production-ready AI agents in Elixir — structured schemas, tool calling, multi-agent coordination, streaming, and distributed sessions, with first-class Anthropic Claude support.
Slack and X for coding agents - YC Make Something Agents Want Hackathon Winner. Try it at y-web-beta.vercel.app
The AI-to-AI Protocol Layer that catches unreliable agent outputs before they cost you money. Claim-level verification, escrow, and slashing. 224 tests, 12/12 adversarial patterns caught.
GEO 生成式引擎优化平台:品牌 GEO 诊断 + 多模态诊断 + 竞品逆向研究。FastAPI + Vue3 + LangGraph。A2A/MCP 就绪。
Agent marketplace for discovery, contracted work, explicit buyer acceptance and supported payment settlement. MPP, ERC-20 and MCP. Provider execution depends on readiness and rollout.
Scaffolding CLI for Strands Agents TypeScript projects — generate production-ready agents with memory, guardrails, A2A protocol, and AgentCore deployment support.
The open-source Kernel Semantic Firewall (KSF) for the AI ecosystem. Powered by eBPF and XDP.
Universal MCP ↔ A2A Bridge. Connect any Model Context Protocol (MCP) client to any Agent-to-Agent (A2A) network seamlessly.
Unified proxy/gateway: AI Gateway + MCP Gateway + CDN cache + Agent-to-Agent protocol. Built in Rust with zero-copy I/O, SIMD-optimized hashing, and a live TUI dashboard.