How do I deploy Nanobot + Ollama on Railway?

You can deploy Nanobot + Ollama on Railway by clicking the "Deploy Now" button on this page. Railway will automatically set up all the necessary services and configurations for you.

What are the system requirements?

Railway handles all the infrastructure requirements. You only need a web browser to deploy and manage your application.

Is this template free to use?

Yes, this template is free to use within your existing Railway account.

Can I customize this template?

Yes, you can fully customize this template. After deployment, you will have full control of what you've deployed in your Railway project.

How do I get support for this template?

You can get support through our community forum: nanobot-f6583263, or click "Get template help" for this template for more assistance.

Deploy and Host Nanobot + Ollama on Railway

nanobot is an ultra-lightweight personal AI assistant built in just ~4,000 lines of Python. It connects to LLM providers like Ollama, OpenRouter, Anthropic, OpenAI, or DeepSeek, and integrates with chat platforms including Telegram, WhatsApp, and Feishu. Despite its minimal footprint, it delivers full agent functionality with web search, scheduled tasks, persistent memory, and extensible skills.

About Hosting nanobot

This template deploys nanobot + Ollama + OpenWebUI on Railway, providing a self-hosted AI agent stack with:

A local or remote LLM runtime via Ollama
A web-based interface via OpenWebUI
A configurable nanobot agent that can run continuously and respond to chat platforms or scheduled tasks Railway handles infrastructure, networking, and scaling so you can focus on configuring your agent and prompts.

Common Use Cases

Run a personal AI assistant accessible via Telegram, WhatsApp, or Feishu that can search the web, manage schedules, and remember context across conversations.
Set up scheduled AI tasks using cron-style automation for daily briefings, reminders, or periodic data analysis.
Host a private, self-contained LLM-powered assistant using Ollama models without relying entirely on external APIs.
Experiment with agent workflows, tools, and skills in a lightweight and hackable codebase.

Dependencies for nanobot Hosting

Python 3.9+ – required to run nanobot.
Ollama – for running local LLMs (e.g. Llama, Qwen, Mistral).
LLM Provider API Keys (optional) – OpenAI, Anthropic, OpenRouter, DeepSeek, etc.
Railway Services – for container hosting, environment variables, and persistent volumes.

Deployment Dependencies

nanobot GitHub repository: https://github.com/HKUDS/nanobot
Ollama documentation: https://ollama.com
OpenWebUI repository: https://github.com/open-webui/open-webui
Railway documentation: https://docs.railway.app

Implementation Details

You will need a Telegram bot and key

To Create a bot

Open Telegram, search @BotFather
Send /newbot, follow prompts
Copy the token
You can get your userId using @getidsbot

Why Deploy nanobot 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 nanobot 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.