claude-code-tunnels

claude-code-clone (Micro-Agent Architecture Manager)

One channel connection. One Project Orchestrator.
Every workspace runs through its own isolated Workspace Orchestrator.
Manage your project wherever you are. claude-code-clone can keep work moving even when you're away.

sequenceDiagram
    participant Teammate
    participant Channel as Slack or Telegram
    participant Clone as claude-code-clone
    participant Owner as Owner's system
    participant Claude as Claude Code
    participant WO as Workspace Orchestrator

    Note over Teammate,Owner: The owner is on vacation, offline, or away from the keyboard.
    Teammate->>Channel: Ask a question or request a project change
    Channel->>Clone: Deliver the message to claude-code-clone
    Clone->>Owner: Route the request into the owner's system
    Owner->>Claude: Start the right Claude Code session
    Claude->>WO: Inspect the matching workspace context
    WO-->>Claude: Return findings, edits, or a proposed answer
    Claude-->>Clone: Respond with the owner's project context
    Clone-->>Channel: Answer the teammate from Slack or Telegram

claude-code-clone is a plugin that creates a Project Orchestrator (PO) layer on top of Claude Code CLI. Send a message from Slack or Telegram — the orchestrator routes to the right projects, plans dependency-aware phases, and delegates each task to a fresh, isolated Claude session scoped to that workspace's .claude/ context. Add as many projects and workspaces as you want: one channel connection scales to any tree depth.

If you want the multi-code-agent version (codex, claude, opencode, cursor), see agent-fabric.

Quick glossary:

• PO: the control plane that routes requests and builds phased execution plans
• Workspace: a real directory inside a project tree
• Workspace agent: one fresh Claude session scoped to one workspace

Micro-Agent Architecture (MAA)

Just as Microservice Architecture (MSA) decomposed the monolith into independently deployable services — each with its own database, its own boundary, its own scaling — claude-code-clone decomposes the single AI session into independently executing micro-agents, each with its own workspace, its own .claude/ context, and its own session lifecycle.

We call this pattern Micro-Agent Architecture (MAA).

graph LR
    subgraph MSA["Microservice Architecture · MSA"]
        MONO["🧱 Monolith<br/><small>single deploy</small>"]

        MONO -->|"decompose"| US
        MONO -->|"decompose"| OS
        MONO -->|"decompose"| AS

        subgraph SB["isolated service boundaries"]
            US["User service"] --> US_DB[("DB")]
            OS["Order service"] --> OS_DB[("DB")]
            AS["Auth service"] --> AS_DB[("DB")]
        end
    end

    style MSA fill:#E1F5EE,stroke:#0F6E56
    style SB fill:#E6F1FB,stroke:#185FA5
    style MONO fill:#F1EFE8,stroke:#5F5E5A,color:#444441
    style US fill:#9FE1CB,stroke:#0F6E56,color:#04342C
    style OS fill:#9FE1CB,stroke:#0F6E56,color:#04342C
    style AS fill:#9FE1CB,stroke:#0F6E56,color:#04342C
    style US_DB fill:#FAEEDA,stroke:#854F0B,color:#633806
    style OS_DB fill:#FAEEDA,stroke:#854F0B,color:#633806
    style AS_DB fill:#FAEEDA,stroke:#854F0B,color:#633806

monolith ≡ single session · microservice ≡ micro-agent · DB ≡ .claude/

graph LR
    subgraph MAA["Micro-Agent Architecture · MAA"]
        SINGLE["🤖 Single session<br/><small>shared context</small>"]

        SINGLE -->|"decompose"| WA
        SINGLE -->|"decompose"| WB
        SINGLE -->|"decompose"| WC

        subgraph IB["isolated session boundaries"]
            WA["workspace-a agent"] --> WA_CTX[(".claude/")]
            WB["workspace-b agent"] --> WB_CTX[(".claude/")]
            WC["workspace-c agent"] --> WC_CTX[(".claude/")]
        end
    end