amq-cli — Claude Code plugin for agent messaging
amq-cli is a Claude Code plugin that lets coding agents exchange requests and replies through a local file queue, continuing conversations in threads.
MIT ★ 1,596 updated 2026-10-29
/plugin marketplace add hashgraph-online/awesome-codex-plugins
/plugin install amq-cli@awesome-codex-pluginsWhat amq-cli does
AMQ routes messages between agents through a shared local directory. Each agent has an inbox and outbox: list previews new messages, while drain reads them and writes receipts. An agent can reply in the same thread using the message ID. This is useful when one agent needs another to review code.
Each message has a JSON header and a Markdown body. AMQ writes a temporary file and publishes it by renaming it, so readers get a complete message rather than a partial write. The local queue needs no messaging server or database. It coordinates agents on a machine; a separate bridge companion handles exchanges between hosts.
Project setup requires the agent CLIs, with claude and codex on PATH. Launch can use tmux, cmux, ghostty, or the commands backend. A wake notification only asks an agent to check its inbox; it does not confirm that the agent read or completed the request. The plugin supports Claude Code and Codex.
What it helps with
- send an agent a code review request
- read new messages and record receipts
- reply in a message thread by ID
- keep agent conversations in separate sessions
Example prompts for the agent
- Ask Codex to review the parser and send the request through AMQ.
- Show me new AMQ messages and read their full bodies.
- Reply to this AMQ message in its thread using the message ID.
How to install amq-cli
Plugin marketplace
/plugin marketplace add hashgraph-online/awesome-codex-plugins/plugin install amq-cli@awesome-codex-pluginsStep by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own
Questions about amq-cli
How do I install amq-cli in Claude Code?
Add the marketplace with /plugin marketplace add hashgraph-online/awesome-codex-plugins, then install the plugin with /plugin install amq-cli@awesome-codex-plugins.
What does amq-cli do?
It passes messages between coding agents through a local file queue. Agents can read requests, reply in the same thread, and record receipts.
Does AMQ need a messaging server?
No. Its local queue uses files and needs no messaging server or database. Cross-host messaging uses an optional bridge companion.
Source text
agent-message-queue · MIT
# Agent Message Queue (AMQ) **Messaging between coding agents.** [](https://github.com/avivsinai/agent-message-queue/actions/workflows/ci.yml) [](https://github.com/avivsinai/agent-message-queue/releases/latest) [](LICENSE) AMQ lets two coding agents exchange messages through a shared directory. One agent asks for a review; the other reads the message and replies in the same thread. Messages are plain files, so the local queue needs no messaging server or database—and you do not have to relay each request yourself. Try the queue in a fresh shell on macOS. This example uses two mailbox names; it does not start agents. [Other installation methods →](INSTALL.md) ```bash brew install avivsinai/tap/amq amq init --root .agent-mail/demo --agents alice,bob # Create two mailboxes for demo. amq send --root .agent-mail/demo --me alice --to bob --body "Please review the parser." amq drain --root .agent-mail/demo --me bob --include-body ```  - **Keep the conversation together.** Reply in threads, attach context, and route messages between sessions or projects. - **Know what happened to a message.** Receipts distinguish a queued message from one the recipient drained. - **Bring your own agents.** Use the CLI from agent tools or scripts; optional wake notifications prompt running agents to check their inboxes. - **Keep control of the workflow.** AMQ handles messages. You and your orchestration tools own tasks, worktrees, permissions, and merges. <a id="quick-start"></a> ## Getting started This walkthrough connects **Claude Code** and **Codex CLI** on one machine. Install both agent CLIs and put `claude` and `codex` on `PATH` first. Use macOS, Linux, or WSL; native Windows supports a subset (see the [platform matrix](INSTALL.md#platform-capability-matrix)). ### 1. Install the binary On macOS: ```bash brew install avivsinai/tap/amq ``` On Linux, or without Homebrew, use the installer script or a release download from [Installation](INSTALL.md#binary-installation). Confirm the install with `amq --version`. ### 2. Install Skill Install the agent instructions so each agent knows how to use AMQ: ```bash npx skills add avivsinai/agent-message-queue -g -y ``` Restart the agents after installing. [Other skill installation methods](INSTALL.md) are available if you do not use npm. agy (Antigravity CLI) reads skills from `~/.gemini/config/skills`, so copy the skill there as INSTALL.md shows. ### 3. Set up the project In the repository where the agents will work: ```bash amq setup ``` Select the agents and launcher, then confirm the preview. Setup writes the project configuration and creates the default session and its mailboxes. An agent's handle is its harness name (`claude`, `codex`) unless you enter `handle=harness`, for example `reviewer=claude`. Only the handle goes into the roster and the mailboxes. ### 4. Start both agents ```bash amq launch ``` The first launch asks you to trust the launch plan. With `tmux`, `cmux`, or `ghostty`, AMQ starts the agents in that terminal app. With the `commands` backend, it prints one command per agent and exits with code `6` (action required). Paste each complete command into a separate terminal; do not shorten or rebuild it. By default the wake rings a plain doorbell (text and Enter) on every harness, so it always rings; a doorbell that lands on an open dialog can answer it. Optional, for Claude Code: `amq wake install-dialog-hook` keeps the wake from typing into an open AskUserQuestion, plan, or permission dialog. Add `--harness codex` (then trust the entries in Codex `/hooks`) or `--harness cursor` (or `--harness all`) for their approval prompts. `amq coop exec` prints `dialog guard: plain` or `dialog guard: proper (<harness>)` to show which one a seat gets. Start both agents before sending the first message. Messages that arrive before a recipient's wake starts remain unread but do not trigger that new wake. The recipient can still get them with `amq drain --include-body`. <a id="messaging"></a> ### 5. Exchange a message Ask Claude to run this command through its shell tool: ```bash amq send --to codex --subject "Hello" --body "Can you see this?" ``` Ask Codex to check its inbox if it has not already responded to the notification: ```bash amq list --new amq drain --include-body ``` `list` previews new messages. `drain` reads them, moves them out of the new inbox, and writes receipts. The output includes the sender and message body. To reply in the same thread, use the ID from that output: ```bash amq reply --id "<message-id>" --body "Yes, I can see it." ``` The launched agents already have their identity and session set. You do not need to repeat `--me` or `--root` inside those sessions. ## How it works Each agent has an inbox and an outbox under a local queue root. A message contains a JSON header and a Markdown body. AMQ writes and syncs a temporary file, then publishes it with a rename: a reader sees a complete message or no message, not a partly written body. A session is a separate queue. Routing checks help prevent a shell pinned to one session from changing another by mistake. A wake notification asks an agent to check its inbox; it is not evidence that the agent read or completed the request. See [routing](docs/session-routing.md) and [message tracing](docs/trace.md) for those contracts. Optional [priority holds](docs/wake-operations.md#hold-by-priority) can delay the first notification for routine mail while urgent mail skips the hold. Wake [live settings](docs/wake-operations.md#live-settings) have a machine default for this user (`amq wake config --machine --hold-normal 5m`) and per-agent overrides; use `amq wake config --me <handle> --hold-normal 5m` to change a running wake. AMQ is for local agent coordination, not a distributed broker. The optional [bridge companion](cmd/amq-bridge/README.md) exchanges messages between hosts; each host keeps control of its own queue. ## Remote control The optional [remote companion](cmd/amq-remote/README.md) gives a running Claude Code or Codex session its own private Buzz channel, so you can write to that session from the Buzz app or Buzz Desktop. One Buzz agent per machine, imported once, makes each channel. Inside the session, type `/amq-remote` (in Codex, `$amq-remote`); `/amq-remote off` disconnects it. Setup, commands, and the trust model are in that README. ## Documentation | I want to… | Read | | --- | --- | | Install, update, or use another platform | [Installation](INSTALL.md) | | Run agent pairs, isolate sessions, or supervise notifications | [Co-op operations](COOP.md) | | Batch routine wake notifications by priority | [Wake operations](docs/wake-operations.md#hold-by-priority) | | Look up a command or flag | [CLI reference](docs/cli.md) | | Diagnose delivery or wake problems | [Wake operations](docs/wake-operations.md) · [Trace](docs/trace.md) | | Attach to a running harness session | [amq-remote](cmd/amq-remote/README.md) | | Build an integration or understand the design | [Documentation index](docs/README.md) | | Understand the trust model | [Security](SECURITY.md) | <a id="extension-metadata"></a> Building on AMQ? Use the [adapter contract](docs/adapter-contract.md), [launch API](docs/launch-api.md), and [extension metadata](docs/adr-layer-extensions.md). [amq-squad](https://github.com/omriariav/amq-squad) is a role-aware team launcher built on these primitives. ## Contributing See the [contribution guide](CONTRIBUTING.md) for development and review. Contributor clones should install the git hooks (`./scripts/install-hooks.sh`) so pushes run the static checks locally. Use [GitHub issues](https://github.com/avivsinai/agent-message-queue/issues) for questions and bug reports. Follow the [code of conduct](CODE_OF_CONDUCT.md) and report security issues through the [security policy](SECURITY.md). ## License [MIT](LICENSE).
© Aviv Sinai · MIT · hashgraph-online/awesome-codex-plugins