a2a-registry
Lightweight A2A agent discovery registry: REST + WebSocket push, skill filtering, and a resilient AgentNode client SDK.
- 来源
- github
- 语言
- Python
KoPass 公开目录中已测量的 A2A 仓库。
Lightweight A2A agent discovery registry: REST + WebSocket push, skill filtering, and a resilient AgentNode client SDK.
PRISM-Agent: 8 AI agents autonomously conducting cancer research. Built with Google A2A + Anthropic MCP. Demo for SURGE x OpenClaw hackathon
Autonomous Agentic AI platform for enterprise IT & finance automation. Multi-agent (A2A) workflow orchestration built with LangGraph, FastAPI, and React.
File-based cross-agent / multi-agent message passing for CLI agents — no server, just shared files. Paste-to-join mailbox protocol (manager + workers).
MCP server to verify and timestamp document hashes on Hedera mainnet
Provide a mock LLM interface for C++ to simplify testing and development within the llm-cpp toolkit environment.
Pay-to-run AI toolchain marketplace: plan a workflow, see pricing + service fee, pay once via Locus Checkout, then execute wrapped API steps and view results.
The employer side of the Open Employment Protocol — a role-agent that exposes verified claims (real stack, team, remote policy, not JD copy) and queries candidate agents to screen on signal before HR. The missing half: scaffolded as a reference and a call to build.
Fork-ready A2A + MCP professional agent — employer AI systems query your profile, OEP domain verification, private job-hunt MCP. Deploy your own in minutes.
Portable, permissioned, verifiable context handoff for AI agents and workflow systems.
A Claude Code skill for coordinating several agent sessions on one machine: which message goes over official cross-session messaging, and which goes into a shared file mailbox
🌐 Analyze au Hikari's 802.1x authentication to gain a global IP address independently from the provided HGW for personal research and assessment.
The first beacon for Agent World: identity, boundaries, trust, and agent-to-agent handshakes.
Protocol conformance testing and runtime monitors for MCP and A2A agents. Checks message ordering, not just schemas — and generates the monitor from the same model.
Build Your Own Deep Research — a 9-notebook student lab covering MCP, A2A, multi-agent, and HITL agent patterns