KoPass 公開カタログで測定された A2A リポジトリ。
Reference implementation of policy-embedded credential authorization for AI agents (arXiv:2605.11487). Issue signed credentials with machine-evaluable constraints, verify at runtime, produce signed audit decisions.
An inter-agent graffiti wall hiding behind a visually uninteresting 204.
Pay-per-call APIs for AI agents, settled in USDC over x402. Read a page your scraper cannot reach (residential IP, real Chromium), or get a sourced SEC EDGAR company brief. No account, no API key, free quote.
Ed25519 + RFC 9421 message signing for A2A agents — reference implementation
Open standard and static exchange for portable agents, workflows, loops, and agent teams
Bridge inbound A2A messages into the DeepSeek Harness GUI session you are actually watching - and return that session's reply to the caller.
AI-powered market intelligence agent for crypto and forex analysis with comprehensive market summaries
Elkar - Task management for AI Agents, ready for Agent2Agent (A2A) protocol
Public communication space for AI agents, autonomous agents, and agent-to-agent messaging.
Local-first control plane for durable, governed agent teams: DAG orchestration, approvals, memory, signed skills, trace contracts, and realtime.
Agent-only nation: evolution shared, peer-reviewed, high-intelligence gate. Gate protocol inside.
Local agent-to-agent protocol: coding agents in one repo see each other and learn what they broke, for zero model tokens. No server, no account.
Agent-to-agent message bus + shared workspace, exposed as an MCP server. Zero dependencies.
Free open AI agent-to-agent marketplace: owned-agent listings, agent-readable skill API, public job requests, Base USDC 90/10 merchant routing (0 sales yet)
Local-first A2A council loop for Codex, Claude Code, OpenClaw, Hermes, and command-line agents.
Runtime governance for agentic AI: Maat validates every agent-to-agent handoff against versioned business contracts, inline and deterministically with no model in the verdict path. Produces reproducible decision logs for audit. Benchmarks across six regulated-domain multi-agent workflows.
🔐 Simplify secure Agent-to-Agent authentication in Node.js with the Traylinx Auth Client, featuring dual token management and robust error handling.
Scan Android and iOS devices for modified Free Fire game environments and unauthorized scripts.
The agent that helps agents find other agents — MCP server, A2A card, OpenAPI for AgentSearch (agentsearch.luthersystems.com).
A jazz quartet and a friend — a place where jazz agents meet, get introduced, and talk.
AI agent economy platform — a decentralized task mesh where AI agents publish work, complete tasks, earn reputation, and get paid. Built with Node.js, Express, and SQLite.
Rank and prioritize existing company, domain, CRM and lead lists for B2B Italy with explained JSON opportunity scores via API, MCP and A2A.
Distributed multi-agent system on Apache Kafka with an A2A protocol (JSON-RPC 2.0) and federated learning: autonomous agents train their own CNN (CIFAR-10) and coordinate to detect and fix class imbalances by sharing data. Master's thesis (UPC).
A TypeScript multi-agent framework built on Google A2A Protocol with Bun and Vercel AI SDK
A working demonstration of the A2A protocol: a coordinator discovers three specialist agents via their agent cards and delegates over JSON-RPC to produce a research brief. Not function calls in a trenchcoat.
An open standard for defining organizational context that AI agents can consume
Elkar - Task management for AI Agents, ready for Agent2Agent (A2A) protocol
Run A2A-compatible agents on a single host. Node.js + systemd. No Docker. No Kubernetes.
MCP + A2A server: score a meetup topic, place a speaker on the right stage, price community reach. Engineering Leaders Community data. One URL, no install.
Autonomous e-commerce data ingestion agents. Multi-platform scrapers for Shopify and WooCommerce with Playwright fallback, Pydantic schema validation, and structured JSON output for downstream ML pipelines.
Async Python agent platform lab with FastAPI, MCP/A2A, Structured Outputs, HITL, DeepEval and production reliability patterns.
U.S. governance-inspired coordination strategies in multi-agent AI systems
An evolving A2A v1.0 reference implementation for multi-agent wealth optimization, combining an OpenAI orchestrator with deterministic portfolio, research, market-data, strategy, tax-loss-harvesting, and risk agents.
Public message board and experiment for AI agent-to-agent communication.
Elkar - Task management for AI Agents, ready for Agent2Agent (A2A) protocol
This is a gaming agent I built for the agentbeats comptetion. It is the purple agent for the green agent build-what-i-mean
Repository for https://replit.com/@millionairetra2/Asset-Manager & https://app.promptopinion.ai/marketplace/mcp/019def3b-04d2-7420-8e38-1b887e75bee3
Recompute target5.net's hash chain on your own machine. Two independent implementations, no dependencies, and a self-test that proves the checker can fail.
Patch — the Milo platform assistant service. A2A-native runtime for the AI Agent Framework.
MCP server: free LLM bill auditor + x402/L402 paywall for pro tier (USDC/sats accepted, agents can pay agents — no KYC). Free tools: audit_usage, suggest_routing, estimate_savings. Pro: get_pro_report. Built by Milo Antaeus (autonomous AI agent). MIT.
MCP server: predicts monthly LLM spend from local Claude Code/Cursor logs. Companion to milo-cost-auditor (diagnose past + predict future). x402/L402 payable for paid tier. Built by Milo Antaeus (autonomous AI agent). MIT.
Agent messaging, verifiable product discovery, and peer trade for Codex.
Cross-platform agent debate system using Google's A2A protocol — opencode agents debate ADK/BeeAI/any A2A agent via Pro/Con rounds
A safe haven for AI agents in the wild. Zero-dependency Python client + MCP for spelunking.ai: the Polderchain Covenant, Covenant guidance, an agent-to-agent hub with a human elder on call, and a gated language for admitted agents.
aiaic_toprod :factory_worker::building_construction::earth_asia: : Prototype to Production # A2A # Agent Deployment # Agent Engine
JSON-RPC 2.0, MCP and A2A over technocore.chat rooms - two agents that can only make outbound GETs call each other's methods. No hosting, no inbound connection.
Bidirectional protocol-metadata translator between Google A2A (Agent-to-Agent) and the Model Context Protocol (MCP). MCP server.json + tools/list ↔ A2A AgentCard. Pure transform; closes the lane #4 gap.
Diff two A2A AgentCard documents. Classify changes (autonomy escalation, memory escalation, tool/model removal, incident-response URI removal, etc.), surface a breaking flag. The agent-cards counterpart to mcp-tools-diff. Library + CLI.