Agent Switchboard

Stacks

Run a team of coding agents

Keep several coding agents working at once: see which need you, keep their work apart, hand off between them and review before you push.

4 tools · API · MCP · CLI

In this stack · 4

  1. Corgi

    CLI

    Runs your coding agents in a terminal multiplexer that shows which are working, finished or need you, with a scriptable…

    VerifiedNewby tals · Code & DevTools, Orchestration · 4 skills · No auth

    Why Shows which of your Claude Code, Codex, Pi or OpenCode sessions are working, finished or waiting for you, in one terminal.

  2. Container Use

    MCP · CLI

    MCP server that gives coding agents isolated containerised environments in separate git branches, enabling multiple…

    Verifiedby Dagger · Infrastructure & Ops · 3 skills · No auth

    Why Gives each agent its own container on its own git branch, so they can work in parallel without conflicts.

  3. ai-memory

    CLI · MCP · API

    Gives coding agents self-hosted shared memory and handoffs, so work carries across Claude Code, Codex, Cursor, and…

    VerifiedNewby Fabio Akita · Memory & State, Code & DevTools · 5 skills · Bearer Token

    Why Passes work from one agent to the next with a handoff that says where it stopped, what failed and what is still open.

  4. OpenQodex

    CLI · MCP

    Reviews coding-agent changes before you push, using scanners plus a separate Claude Code or Codex reviewer, and gives…

    VerifiedNewby Qodex · Code & DevTools, Security · 5 skills · No auth

    Why Reviews each agent's changes before you push, with scanners and a separate Claude Code or Codex reviewer.

/stacks/coding-agent-team
4 tools · access api+mcp+cli · in order
Keep several coding agents working at once: see which need you, keep their work apart, hand off between them and review before you push.
in this stack
corgicliShows which of your Claude Code, Codex, Pi or OpenCode sessions are working, finished or waiting for you, in one terminal.container-usemcp+cliGives each agent its own container on its own git branch, so they can work in parallel without conflicts.ai-memorycli+mcp+apiPasses work from one agent to the next with a handoff that says where it stopped, what failed and what is still open.openqodexcli+mcpReviews each agent's changes before you push, with scanners and a separate Claude Code or Codex reviewer.
more
/stacksevery stack/api/stacks/coding-agent-teamthis stack as JSONGET · no auth