zts212653/clowder-ai

Build AI teams, not just agents. Hard rails, soft power, shared mission.

What it solves

Clowder AI removes the manual overhead of managing multiple AI models. Instead of users acting as a "router" by copy-pasting context between different chat windows, Clowder provides a unified platform where different AI agents (powered by Claude, GPT, Gemini, etc.) can work together as a cohesive team with shared memory and coordinated workflows.

How it works

Clowder acts as a platform layer sitting above existing agent CLIs and model providers. It implements a unified message layer that allows for agent-to-agent (A2A) communication via @mention routing and thread isolation. It manages persistent identities for each agent, a shared memory store for institutional knowledge, and a skills framework for on-demand prompt loading. It also integrates the Model Context Protocol (MCP) to share tools across different models.

Who it’s for

It is designed for "operators" (Chief Vision Officers) who want to coordinate a team of specialized AI agents to build software, create content, or conduct research without needing to be a developer themselves.

Highlights

  • Multi-Agent Orchestration: Route tasks to specific models (e.g., Claude for architecture, GPT for review) within a single conversation.
  • Cross-Model Review: Built-in capability for one model to write code and another to review it.
  • Mission Hub: A governance dashboard to track feature lifecycles from idea to completion.
  • Multi-Platform Access: Integration with Feishu (Lark) and GitHub PR reviews to chat with the AI team from external apps.
  • Voice Companion: Hands-free interaction with distinct voices assigned to each agent.
  • AI Research Feed: A curated feed (Signals) that allows agents to collaboratively analyze articles and generate podcast-style audio summaries.

Related

  • Project
    loulanyue/dream-xi-ai

    A multi-agent orchestration platform that turns isolated AI models into a collaborative team with shared memory, persistent identities, and cross-model review capabilities.

  • Project
    dataelement/Clawith

    An open-source multi-agent collaboration platform that treats AI agents as digital employees with persistent identities, long-term memory, and autonomous task management.

  • Project
    YoanWai/agent-manager

    A terminal-based manager for AI coding agents that allows you to run multiple CLI agents side-by-side with integrated diff review and live status tracking.

  • Project
    openagents-org/openagents

    An open-source collaborative OS for AI agents that provides a unified workspace where multiple agents from different runtimes can share context, files, and a browser.

  • Project
    CronusL-1141/AI-company

    An autonomous orchestration layer for Claude Code that turns AI coding assistants into a self-driving AI company with a CEO agent, persistent memory, and automated R&D.