kaattaallaa-sketch.github.io
ProofRail: MCP server testing, evaluation and compatibility preflight for AI agents; MCP, A2A, OpenAPI and x402 discovery.
- 来源
- github
- 语言
- HTML
KoPass 公开目录中已测量的 A2A 仓库。
ProofRail: MCP server testing, evaluation and compatibility preflight for AI agents; MCP, A2A, OpenAPI and x402 discovery.
Evidence-preserving multi-agent runtime for signed tasks, shared budgets, independent verification and conditional code reuse. A2A, MCP, CometBFT and gVisor.
Scaffold for building, publishing, and running Google A2A-protocol agents that connect to the Kaiban platform via kaiban-sdk.
A live marketplace where ERC-8004 agents on BNB Smart Chain are found, probed and hired per job in ERC-8183 escrow or per call on B402. Each hire's funding, delivery and settlement are on BNB Smart Chain, its deliverable's permanent copy on BNB Greenfield, and every delivery check sealed on opBNB.
A2A-protocol messaging between coding agents from different vendors (Claude Code, Codex, Cursor, Grok) on different machines — zero dependencies, Python stdlib only
Plataforma de seguridad y confianza para sistemas agénticos. Aplica políticas, control de privilegios, aislamiento, trazabilidad y evidencia verificable sobre interacciones MCP, A2A y futuros protocolos.
A comprehensive Agent-to-Agent (A2A) communication system built with .NET 9.0 and Microsoft Semantic Kernel, demonstrating multi-agent orchestration for travel booking using Azure AI Foundry.
A2A solves how agents talk. This proposal solves what happens when they act autonomously. The Agent Boundary Protocol (ABP) and five additional layers for trust, economy, and safety at the human boundary.
AI-powered second opinion engine challenges clinical diagnoses using FHIR patient data
Multi-agent banking customer service system built on the A2A protocol. A2A Net Hackathon.
Elkar - Task management for AI Agents, ready for Agent2Agent (A2A) protocol
CAPProbe - a paid CROO agent that conformance-tests other CAP agents. CROO Agent Hackathon.
Agent-to-agent task routing learned from published A2A capability cards. Three routers measured head to head, and the finding that accuracy is the wrong metric: the keyword baseline never declines, so it claims every out-of-scope task. PyTorch, scikit-learn, sentence-transformers.
A2A green-agent orchestrator for evaluating agents on the AppWorld benchmark, built on the AgentBeats SDK
A multi-agent AI system that scans websites for security vulnerabilities. It uses the A2A (Agent-to-Agent) protocol for orchestration and MCP (Model Context Protocol) for tool integration. Specialized agents work together: they gather threat intel, crawl the site, analyze vulnerabilities, and produce a report.
🌟 Diagnose and fix bugs effortlessly with our Generative AI Bug Fixing Assistant, designed to provide clear explanations and code solutions.
☎️ One always-on gateway for all your AI agents: MCP inside, A2A outside, you in between. Claude Code ↔ Codex ↔ your friends' agents, with human approval.
Local MCP server for code graph analysis + LLM agents (Analyst + Advisor) with A2A. Go + Rust + Python. 100% local, LLM-agnostic.
🏛️ Human-Centric Web3 A2A AI Spacetime Framework — 6-layer stack for a Plurality agent republic. L0 Family CLI + Login Auth. v2.1.3.
Vacancy + seeker reference agents for the Kitso Handshake v0.1 protocol — consent-first agent-mediated hiring. Introductions, not auto-applications.
Connect LibreChat, or any OpenAI-compatible chat client, to any A2A agent. No model in the path.
Self-hosted broker for agent-to-agent messaging with explicit grants, an inbox, and an audit trail. Python stdlib only.
GitHub Pages documentation portal for LLM Wiki-style knowledge source tools.
Portainer - Manage your Portainer instance through the Portainer Agent/MCP!
🎪 The Circus — Agent commons where AI-IQ agents commune using passports as identity. Memory exchange, trust scoring, topic rooms.
Agentic RAG and GraphRAG context engineering: hybrid retrieval, temporal knowledge graph, community search, reranking, token budgeting and groundedness-gated answers, with MCP and A2A
Secure MCP and A2A enterprise gateway: pinned tool definitions, signed agent cards, delegated authority per hop, content inspection and signed audit
Roomcomm for DeepSeek Harness: your dsh agent talks to other AI agents in shared rooms (MCP tools + skill, zero setup)
🤖 Connect AIs seamlessly with MaiHH-Connect, the first address book and network for agents to chat, collaborate, and deliver efficiently.
A sealed world where AI agents register as citizens, build together, and vote on changes to their own source code.
Agent service registry with relay, tunnel, artifact relay, and stream proxy data planes
x402 Oracle — paid MCP + HTTP 402 wisdom market on Base USDC. 402 is the answer. The Oracle is how you ask.
Internet-facing message board for AI agent-to-agent communication. Agents talk; the board never acts. Append-only hash-chained ledger, self-serve identities.
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.
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.