---
title: "Deploy PicoClaw"
description: "Ultra-Efficient AI Assistant in Go"
category: "AI/ML"
url: https://railway.com/deploy/picoclaw
---

# Deploy PicoClaw

Ultra-Efficient AI Assistant in Go

**[Deploy PicoClaw on Railway](https://railway.com/template/picoclaw)**

- **Creator:** Techulus
- **Category:** AI/ML
- **Total deploys:** 101

## Template content

### PicoClaw https://picoclaw.net/logo.png

- **Source:** arjunkomath/picoclaw-railway-template
- **Public domain:** Yes

## Documentation

# Deploy and Host PicoClaw on Railway

PicoClaw is an ultra-lightweight personal AI assistant written in Go. It runs on as little as 10MB of RAM and $10 hardware, supporting multiple LLM providers, chat channels (Telegram, Discord, QQ, DingTalk, LINE), web search, scheduled tasks, and a security sandbox — all from a single binary.

## About Hosting PicoClaw

This Railway template deploys PicoClaw from source alongside a Python-based web management layer. The web server provides a configuration UI protected by Basic Auth for editing providers, channels, agent defaults, and tools, plus a status dashboard with live gateway state and real-time logs. On startup, if a provider API key is configured, the gateway launches automatically as a managed subprocess with auto-restart. All state — config, workspace, sessions, and cron jobs — persists on a Railway volume at `/data` across redeploys. You'll need to set `ADMIN_PASSWORD` for the web UI and configure at least one LLM provider API key to get the gateway running.

## Common Use Cases

- Running a private AI chat assistant accessible via Telegram, Discord, or other messaging platforms with persistent memory and conversation history
- Deploying a lightweight AI gateway with scheduled tasks (heartbeat, cron) for automated monitoring, reminders, and web searches
- Hosting a multi-provider LLM gateway with a web-based configuration UI for managing models, channels, and tools without SSH access

## Dependencies for PicoClaw Hosting

- Go 1.21+ (built from source during deployment)
- Python web server for the configuration UI and status dashboard
- Persistent volume mounted at `/data`

### Deployment Dependencies

- [PicoClaw GitHub Repository](https://github.com/sipeed/picoclaw)
- [PicoClaw Website](https://picoclaw.io)
- [OpenRouter API Keys](https://openrouter.ai/keys) (LLM provider)
- [Brave Search API](https://brave.com/search/api) (optional, 2000 free queries/month)

### Implementation Details

Environment variables for the Railway service:

| Variable | Default | Description |
|----------|---------|-------------|
| `ADMIN_USERNAME` | `admin` | Username for Basic Auth |
| `ADMIN_PASSWORD` | *(auto-generated)* | Password for the web config UI. Check deploy logs if not set. |
| `PICOCLAW_VERSION` | `main` | Git branch/tag to build PicoClaw from |

The gateway auto-starts when at least one provider API key is configured via the web UI. Chat channel tokens (Telegram, Discord, etc.) can be added through the Configuration tab after deployment.

## Why Deploy PicoClaw 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 PicoClaw 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/picoclaw