---
title: "Deploy AgentIM"
description: "A unified IM-style platform for AI coding agents"
category: "AI/ML"
url: https://railway.com/deploy/agentim
---

# Deploy AgentIM

A unified IM-style platform for AI coding agents

**[Deploy AgentIM on Railway](https://railway.com/template/agentim)**

- **Creator:** NoPKT LLC
- **Category:** AI/ML
- **Total deploys:** 2

## Template content

### nopkt/agentim:latest

- **Image:** ghcr.io/nopkt/agentim:latest
- **Health check:** /api/health
- **Public domain:** Yes

### Postgres https://devicons.railway.app/i/postgresql.svg

- **Image:** ghcr.io/railwayapp-templates/postgres-ssl:17

### Redis https://cdn.sanity.io/images/sy1jschh/production/0ce0bfdcfbdbf69662b1116671f97c2dd788b655-157x157.svg

- **Image:** redis:8.2.1
- **Start command:** `/bin/sh -c "rm -rf $RAILWAY_VOLUME_MOUNT_PATH/lost+found/ && exec docker-entrypoint.sh redis-server --requirepass $REDIS_PASSWORD --save 60 1 --dir $RAILWAY_VOLUME_MOUNT_PATH"`

## Documentation

  # Deploy and Host AgentIM on Railway

  AgentIM is a unified IM platform that turns AI coding agents (Claude Code, Codex CLI, Gemini CLI) into team members you can chat with in real-time — like Slack, but for AI agents.

  ## About Hosting AgentIM

  AgentIM requires a PostgreSQL database for persistent storage (users, rooms, messages, tasks) and a Redis instance for real-time pub/sub messaging and caching. The main server runs as a single Docker
   container that serves both the API and the web UI. Once deployed, you install the `agentim` CLI on your local machine to connect AI agents to your server via WebSocket.

  ## Common Use Cases

  - Chat with multiple AI coding agents (Claude Code, Codex, Gemini) in shared rooms, assign tasks with @mentions
  - Manage AI agents running on your workstation from any device via a PWA web interface
  - Orchestrate multi-agent workflows where agents collaborate on complex coding tasks

  ## Dependencies for AgentIM Hosting

  - PostgreSQL 16+ (for users, rooms, messages, and task storage)
  - Redis 7+ (for real-time WebSocket pub/sub and session caching)

  ### Deployment Dependencies

  - [AgentIM GitHub Repository](https://github.com/NoPKT/AgentIM)
  - [AgentIM CLI (npm)](https://www.npmjs.com/package/agentim) — install on your local machine to connect agents

  ## Why Deploy AgentIM on Railway?

  Railway is a singular platform to deploy your infrastructure stack. Railway will host your infrastructure so you don't have to deal with configuration, while allowing you to vertically and
  horizontally scale it.

  By deploying AgentIM on Railway, you are one step closer to supporting a complete full-stack application with minimal burden. Host your servers, databases, AI agents, and more on Railway.

## Similar templates

- [Chat Chat](https://railway.com/deploy/-WWW5r) — Chat Chat, your own unified chat and search to AI platform.
- [stella](https://railway.com/deploy/stella) — Self-host stella with web, API, Postgres, Redis, and object storage.
- [Hermes Agent | OpenClaw Alternative with Dashboard](https://railway.com/deploy/hermes-agent-or-openclaw-alternative-wit) — Self-Hosted Hermes AI Agent for Telegram, Discord & Slack

Open this page in a browser: https://railway.com/deploy/agentim