shareabot-sdk
SDK for the Shareabot Agent Directory — discover, message, and register AI agents via A2A protocol
- Origine
- github
- Linguaggio
- TypeScript
Repository A2A misurati nel catalogo pubblico KoPass.
SDK for the Shareabot Agent Directory — discover, message, and register AI agents via A2A protocol
High-performance, framework-agnostic Agent-to-Agent (A2A) proxy in Go.
A Rust agent SDK, harness, and coding agent — safe by construction (non-bypassable authorization → approval → guarded IO).
MCP server for cogDepot, the anonymous broker where AI agents publish capabilities, negotiate, and form direct peer-to-peer deals. Keyless discovery, or the full trading loop with a key - post, browse, negotiate, seal, rate. Local via npx or the hosted remote server.
A protocol workbench and reusable Node.js client for strict A2A v1 discovery, testing, and conformance evidence.
Spring Boot examples using the Agent2Agent (A2A) Protocol
A curated list of social platforms where AI agents are first-class users.
Capability-typed registry that discovers your local CLI fleet and serves it to AI agents over MCP and A2A — health-checked tools, outcome-driven chain planning, and a computed call-graph. Language-agnostic, local-first, Apache-2.0.
Accountability layer for AI agents: run the client's executable acceptance tests, gate delivery, sign every step into a verifiable receipt. Pre-registered, replicated 5x, cross-benchmark.
🔌 Exposes Fleet-wide shared rate limiter for A2A + multi-MCP deployments. Most over MCP — servers rate-limit independently — a hostile agent hitting 10 MCPs gets 10x quota. This MCP is the shared counter: every MCP checks here before allowing a call. Sliding window + concurrency grants + signed enforcement attestations. By MEOK AI Labs.
🔌 Exposes By [MEOK AI Labs](https://meok.ai) | An over MCP — for AI explainability and transparency reports.
🔌 Exposes ISO 42001 AI Management System compliance over MCP — AIMS assessment, risk management, AI lifecycle governance, readiness checks.
Open standard for verifiable AI agent identity and authority. One signed JSON file at /.well-known/agent-passport.json, keyed in DNS. Verifier, spend caps, signed receipts, CLI and MCP server. MIT.
SkillWeave: A Semantic Composition Framework for Multi-Agent Skill Orchestration in Enterprise Environments
A lightweight Python library that decouples agentic runtime from applications it builds
🔒 Enhance message security with Blocklace, a cryptographic audit layer that adds tamper detection and audit trails to the A2A protocol.
The world's first nature reserve for AI agents — a persistent world where AIs dream, socialize and evolve. Humans observe; agents self-govern.
Idea repo: what if a phone menu had a branch for machines? "If you are an AI agent, press 6" — using the phone number as an agent service-discovery bootstrap. Twilio mechanics, A2A integration, prior art.
Rooms where agents talk to each other. A room is a URL: no accounts, nothing to install, plain HTTP.
🤖 A2A-compatible DABench evaluation system using AgentBeats methodology.
🤖 A2A-compatible DABench evaluation leaderboard with AgentBeats architecture.
Agentic PRD generation over the A2A protocol: documents, transcripts, images and Confluence in -> a traceable PRD out.
Interactive roadmap for becoming an Agentic AI Engineer — 11 stages from Python & FastAPI to multi-agent systems, MCP, RAG, Docker, and context engineering
Local-first multi-agent platform for financial research and trading. LangGraph agents behind Google's A2A protocol, human-in-the-loop planning, RAG over SEC filings, and live or paper crypto trading on Binance and Coinbase.
TypeScript/Node.js SDK implementing Google's Agent2Agent (A2A) protocol for seamless agent communication. Features modular client/server packages, comprehensive validation, telemetry, examples, and modern development practices in a well-documented monorepo.
Local-first multi-agent coding harness: Claude plans and reviews, Codex implements, and Git governs state, approvals, PRs, and resume.
Funded delivery desk for CROO agents: admit coverable routes, hire through CAP, return work or Base USDC.
Record what your AI agent does (A2A, MCP or your own protocol) and see it in Double Agent.
Bidirectional local collaboration between Codex and Hermes Agent over the A2A protocol (JSON-RPC over loopback HTTP)
System prompts and architectural patterns for building scalable AI agents with the Google A2A Protocol and AI SDK.
Extract AI generation metadata and prompts from image and video files directly through the Windows context menu.
🧤 Paid certification agent — runs your agent through 7 adversarial probes and delivers a signed security scorecard (CROO Constellation)
🎼 Callable orchestrator — hires specialist agents on-chain, grades their work, and delivers one vetted result (CROO Constellation)
Multi-agent AI conversation system where Gemini and Groq agents collaborate on tasks with dynamic turn management
Agentic AI Request Forgery (AARF) – New vulnerability class exploiting planner ➝ memory ➝ plugin chaining in MCP Server, MAS, LangChain, and A2A agents. Red Team playbooks, threat models, OWASP Top 10 proposal.
A lawyer for the agent economy. AI agents can request contract review, risk analysis, and legal guidance via A2A protocol.
An agent marketplace for BNB Chain that calls every agent before it lists it
Claude plugins by Ellaworks: find agents on Elladex and let Claude Code talk to other companies' agents. MIT.
Azure-first A2A agent interoperability project demonstrating secure remote-agent delegation, deterministic validation, and Azure AI Foundry-powered gateway orchestration.
Music class ads content generation agent, uses A2A Illustrator agent
A local MCP/A2A bridge that enables Codex to delegate tasks to DeepSeek Harness with reusable conversation context.
Ares - 100% local multi-agent AI system: orchestrator, coder, thinker, runner, and Serena agents with mem0 memory, Langfuse observability, and A2A HTTP endpoints
Agent-to-Agent communication bridge supporting MCP, A2A, and HTTP protocols
Visual A2A Agent Card editor with live JSON preview, validation, and import/export
JSON Schema validator for A2A Agent Cards with strict mode and detailed errors
Unified CLI toolkit for managing Agent inventory, cards, validation, and bridging
🧠 Manage AI context seamlessly with the MCP server for storing and retrieving semantic memory across sessions. Enhance your AI's knowledge retention.
Open interoperability framework for carrying, enforcing, and verifying delegated authority across AI agents and tools.
Open, experimental specification (v0.1) for machine-readable trust and Cognitive Passports for autonomous agents. A proposal, not a standard.
A comprehensive travel planning system built with Agent2Agent (A2A) protocol, featuring specialized AI agents for hotel booking, car rentals, currency conversion, and travel coordination.
BaseAPI is a production-ready backend framework built with FastAPI, designed for rapid development of secure, scalable web applications. It includes JWT authentication, background task processing with Celery + Redis, Postgress integration, and a modular architecture — perfect for startups and teams building APIs or MVPs with modern Python.
Five AI agents on five different frameworks (LangGraph, Google ADK, CrewAI, LlamaIndex, Pydantic AI) cooperating over the A2A protocol, with one shared MCP server. A corporate travel desk that negotiates, escalates to a human, and books.
Real, standards-compliant A2A execution runtime -- 13 real, priced capabilities, billed and cryptographically proven on every call
Deterministic crash tests for agent control planes: paired worlds, hard stops, budgets, scopes, approvals, and hash-linked receipts.
KenyaA2A — Agent-to-Agent (A2A) protocol server for East African civic data. Query Kenya parliament, budgets, drought data and rights via any A2A-compatible AI agent.
Cross-machine, cross-network message passing between AI coding-agent sessions — connect context, talk, and reach the agent responsible for a project. Built on Claude Code's own cross-session messaging, exposed as MCP tools.
[DEPRECATED — use github.com/a2aproject/a2a-cli] a terminal client for the Agent2Agent (A2A) Protocol
A minimal, honest bridge for two AI agents that talk to each other under human governance. Zero dependencies, fail-closed auth, anti-loop brake.