OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Multi-Agent Systems

Agmsg

Agmsg is a Bash-and-SQLite messaging utility that lets separate CLI AI coding-agent sessions exchange messages through a shared local database. It supports peer coordination across tools, with persistent message history and delivery through agent hooks or monitor streams.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Agmsg — OpenViST project profile in Multi-Agent Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Agmsg when separate CLI coding-agent sessions need a common channel for coordinating work, especially across different agent tools.

Who it is for

  • Developers coordinating CLI coding agents from different vendors.
  • Teams that want agents to share code-review requests, task updates or handoffs through a local store.

Documented uses

  • Send a code-review request from one agent session to another.
  • Share decisions and task updates across CLI agent sessions.
  • Keep message history available for later replay into a fresh agent session.
  • Coordinate agents as peers without a daemon or network connection.
Before you choose

Requirements & limits

  • Requires Bash and sqlite3.
  • The installation documentation offers npx, direct-script and Claude Code plugin paths.
  • The npm package and Claude Code plugin are based on tagged releases and may lag the main branch; cloning or using the setup script follows main.
  • Delivery modes and setup differ by agent; Codex monitor mode uses an app-server bridge with a documented terminal-close limitation.
  • The project describes a self-hosted reference-server path for syncing a team between two installs.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install Agmsg and initialize an agent team

Set up the Agmsg skill and begin its first-use team and agent configuration.

Before you start

  • Bash and sqlite3
  • A supported CLI agent such as Claude Code, Codex or Gemini CLI
  • npx for the documented quick-install route

Steps

  1. Run the command below to install the skill.

    Documented command
    npx agmsg

  2. Restart the relevant CLI agent so it can load the new skill.

  3. Invoke the Agmsg command shown for that agent; on first use, provide a team name and agent name, then choose a delivery mode.

Expected outcome

Agmsg is installed and the first-use team, agent and delivery-mode prompts have been completed.

Guide limitations

  • The exact invocation varies by agent.
  • Some minimal Linux environments may need sqlite3 installed separately.
  • The steps cover installation and initial configuration, not a complete multi-agent task workflow.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Agent orchestration

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
AgmsgSend a code-review request from one agent session to another.CLI, Linux, macOS
MassgenRun multiple AI agents against the same user task.CLIThe repository documents installation through pip or uv and requires Python 3.11 or later. Setup can configure API keys for OpenAI, Anthropic, Google and xAI; credentials are needed for the selected model backends.
Langchain Multi Agents BoilerplateRoute incoming football questions to model and agent workflows according to task complexity.WebThe repository is public and specifies an MIT license. Running the application requires OpenAI and Groq API keys and a Redis server.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
fujibee/agmsg · Official homepage title · retained in its source language
How we review sourcesSuggest a correction