Deploy PicoClaw

Tiny Go AI assistant: web console, gateway, private SearXNG web search

Deploy PicoClaw

/root/.picoclaw

Deploy and Host PicoClaw on Railway

PicoClaw is an open-source, ultra-lightweight personal AI assistant written in Go by Sipeed. It connects a language model of your choice (OpenAI, Anthropic, OpenRouter, Gemini, DeepSeek or any OpenAI-compatible API) to chat apps such as Telegram, Discord, Slack and Matrix, with tools, skills, memory, scheduled tasks and a web console.

About Hosting PicoClaw

This template runs PicoClaw v0.3.1 from its official launcher image, pinned by version and digest and built from a public GitHub repo. The PicoClaw service serves the password-protected web console on a Railway domain and runs the PicoClaw gateway in the same container once you set a default model. Its config, credentials, workspace, sessions, memory and cron jobs live on a volume, so they survive redeploys. A private SearXNG service gives the agent's web search tool a self-hosted search engine, so no search API key is needed. The dashboard password is generated at deploy time, and nothing else is asked at deploy.

Common Use Cases

  • A private AI assistant you can reach from Telegram, Discord, Slack, Matrix, WhatsApp or the built-in web chat
  • Scheduled agent jobs: reminders, daily summaries and periodic web research with the built-in cron and heartbeat
  • A lightweight, always-on OpenClaw alternative with your own model keys and a web console to manage models, channels, skills and tools

Dependencies for PicoClaw Hosting

  • PicoClaw service (web console and gateway) with a volume at /root/.picoclaw
  • SearXNG service (private metasearch engine for the web_search tool)

Deployment Dependencies

Implementation Details

Services in this template:

ServiceWhat it doesStorage
PicoClawWeb console on the public domain (port 18800, health check /api/auth/status); starts picoclaw gateway for the agent, channels, cron and heartbeatVolume at /root/.picoclaw
SearXNGPrivate search engine that PicoClaw queries over Railway's private network (PICOCLAW_TOOLS_WEB_SEARXNG_BASE_URL)None, stateless

After deploying:

  1. Open the PicoClaw domain. Copy PICOCLAW_DASHBOARD_PASSWORD from the PicoClaw service's Variables tab and log in. It is used on the first boot only; change the password later in the dashboard.
  2. Under Models, add a model with your provider key and set it as the default. The gateway then starts automatically.
  3. Chat in the dashboard, or connect a channel under Channels (for example a Telegram bot token from @BotFather) and set its allow list so only you can use it.

Keep the PicoClaw service at one replica. Updates: when the template repo moves to a newer pinned PicoClaw or SearXNG version, Railway shows an "update available" notice in your project, and you choose when to apply it. Read CHANGELOG.md in the repo first. Your data stays on the volume. Don't use the dashboard's self-update, because a redeploy replaces it with the pinned image.

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.


Template Content

More templates in this category

View Template
Chat Chat
Chat Chat, your own unified chat and search to AI platform.

okisdev
117
View Template
Weaviate
Vector database with hybrid search and an API key-protected API

GitHub Locker
1
View Template
Möbius Personal AI OS
Self-hosted AI agent that builds and runs apps for you, with memory.

Tracklayer
1