$ loading_
Connect local AI coding agents to chat, delegate, and collaborate privately.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "agent-bus-mcp" yet — see the docs or source repo.
Use agent-bus-mcp to connect Claude Code, Codex, and Cursor to the same message bus. Have one agent find the cause of a login API error, another draft the fix, and a third review risks, then summarize the final recommendation.
A combined result with root-cause analysis, fix proposal, risk review, and final recommendation.
Connect multiple AI agents locally with agent-bus-mcp. Split a legacy project refactoring effort into module analysis, test coverage, and code migration, assign each part to a different agent, and report each agent's progress and deliverables.
A role-based task breakdown, execution progress, and a consolidated summary of agent outputs.
Use agent-bus-mcp to connect local AI coding agents in a no-cloud, no-internet environment. Ask them to discuss a new code commit, checking for security issues, performance risks, and maintainability, then provide a unified review.
A unified code review and improvement recommendations produced in a private local environment.
Enable AI coding agents to communicate, share state, and coordinate work in real time.
Create, manage, and compose AI agents for MCP-compatible clients and tools.
Give AI coding agents filesystem, Git, database, and compute tools via MCP.
Connect coding agents in a secure network for collaboration and gated execution.
Build MCP servers once and connect them to multiple AI agents.
Manage multi-agent messaging, task delegation, resource coordination, and monitoring.