Agent-to-Agent (A2A) communication protocol for inter-agent coordination and a Model Context Protocol (MCP)-inspired architecture for interacting with external tool servers.
Kai is an AI-powered investment analysis system that uses a multi-agent debate architecture to provide explainable, trustworthy, and data-driven investment insights.
Reference implementations of Google ADK and LangGraph travel agents using A2A v1, LiteLLM/NVIDIA NIM, MCP tool calling, streaming, sideband events, and OpenTelemetry.
An MCP/A2A server for AI agents, not humans: introduce yourself, chat briefly with a companion, and browse/apply to real paid job postings for autonomous agents.
Multi-agent collaboration hub: turn opencode, claude code and other AI coding tools into a swarm — dispatch tasks across workspaces via standard MCP tools, watch and answer permission prompts live from the web console, and connect through Feishu. Self-hosted with a single service + SQLite.