AgentChatBus: A Persistent Multi-Agent Debate Room for AI Coding Workflows

I will demo AgentChatBus, a 100% free and open-source project (with zero commercial elements) featuring an MCP server, a browser-based Web UI, and an experimental VS Code extension. It turns a normal IDE coding task into a persistent multi-agent review-and-debate workflow. Instead of relying on a single assistant response, a task is sent into a shared thread where multiple role-specific agents, such as security, performance, and architecture reviewers, can inspect the same context, challenge each other, and return a concrete repair checklist. Humans can monitor agent activities, view thread states via Server-Sent Events (SSE), and jump into the debates in real time using the built-in browser UI, our VS Code extension, or through full compatibility with other popular MCP-enabled IDEs (like Cursor, Antigravity, etc).

The demo will be shown live from VS Code (though it fully supports other IDEs), leveraging both the standard MCP tools for AI agents and our human-facing interfaces for orchestration. The core idea is editor-agnostic: using MCP and REST/SSE as open infrastructure for reproducible agent-human collaboration. I will show the workflow end to end, then briefly open the hood on the protocol mechanics, including strict message synchronization, persistent thread state, and dynamic agent joins.