Skip to main content
99.99% Uptime SLA Network status

How to Self-Host PicoClaw on a VPS

This guide explains how to self-host PicoClaw on a VPS so the runtime can live in a persistent remote environment instead of depending on a local machine. Virtarix provides the VPS infrastructure. You install, configure, secure, update, and operate the software you run on it. You bring your own PicoClaw setup, provider access, API keys, repositories, tools, updates, and configuration.

20% welcome offer $4.40/mo for first 3 months (then $5.50)
Trustpilot rating: 4.5 out of 5 4.5/5 on Trustpilot

Recommended Quick Setup

Use this path when you want the shortest practical route from VPS order to a usable PicoClaw server workspace. The full checklist below expands each step. Start small, verify the selected PicoClaw release path, keep the gateway private during testing, and scale only after measuring real server usage.

01

VPS plan

Virtarix S / Starter VPS Includes 3 CPU cores, 6 GB RAM, 50 GB NVMe storage, Unlimited bandwidth*, 1 free snapshot, 1 backup included, IPv4 + IPv6, Full root access,

02

Operating system

Use Ubuntu VPS, Debian, or another supported Linux server for the selected PicoClaw runtime path.

03

Access method

Connect with SSH, use root or sudo access for setup, and restrict exposed ports to SSH and the services you intentionally run.

04

Runtime workflow

Use the official precompiled binary for the simplest first test, or source/Docker only when that path fits your update and rollback process.

05

Session continuity

Use tmux, systemd, Docker Compose, queues, or service supervision only after the exact PicoClaw command path has been tested manually.

06

Safety checkpoint

Take a snapshot before major dependency changes, protect provider keys and repository credentials, test one small workflow, and keep rollback notes before exposing any gateway, webhook, or Web UI route.

Who This Guide Is For

This page is for users who want PicoClaw to run from a small, controlled VPS environment instead of experimenting only on a local machine.

Users testing lightweight agent runtimes

Use a VPS when a small always-on environment is enough but uptime, SSH access, and logs still matter.

Builders who prefer a small server footprint

Keep dependencies, environment files, repositories, and process supervision lean while preserving a remote runtime.

Operators who want logs and state on a server

Move runtime output, configuration, credentials, and restart notes into a dedicated server context.

Technical users comfortable reviewing early-stage framework notes

Virtarix provides the VPS infrastructure. You install, configure, secure, update, and operate the software you run on it.

What You Need Before You Start

Before selecting a plan or installing PicoClaw, confirm the server access, runtime path, credentials, firewall exposure, and recovery routine needed for the deployment.

Choose the PicoClaw Runtime Path

Before running commands, decide how PicoClaw should be installed, updated, restarted, and recovered on the VPS. Use current upstream documentation as the authority for exact versions, flags, release assets, checksums, and production-suitability notes. Prefer stable releases for a baseline VPS deployment; use nightly or pre-release builds only when you intentionally accept instability and have a rollback snapshot.

Precompiled binary

Best when you want the simplest lightweight VPS install path for a supported Linux architecture and do not need to modify source code.

Source build

Best when you need to patch, audit, or build PicoClaw with Go and the Web UI toolchain.

Docker Compose gateway

Best when you want config, data, logs, restart behavior, and gateway operation under the Docker Compose setup documented by the current release.

Launcher WebUI

Best for first-time configuration before editing config files directly; keep access local or tunneled until authentication, firewall, and host-binding settings are reviewed. Choose the simplest path that matches your operating model; avoid mixing binary, source, launcher, and container paths until the first deployment is understood.

Recommended VPS Requirements

Minimum starting point for a test environment:

Minimum starting point for a test environment

Use this to validate the workflow before committing to an always-on deployment; the extra headroom is for package builds, logs, Docker, gateway activity, provider tooling, and rollback files rather than PicoClaw alone.

  • 2 CPU cores
  • 4 GB RAM
  • 30 GB NVMe storage
  • Ubuntu VPS, Debian, or another supported Linux server
  • Root or sudo access
  • Backup or snapshot before major changes

Recommended Virtarix starting point

Virtarix S / Starter VPS

20% off your first 3 months - normally $5.50/month

  • 3 CPU cores
  • 6 GB RAM
  • 50 GB NVMe storage
  • Unlimited bandwidth*
  • 1 free snapshot
  • 1 backup included
  • IPv4 + IPv6
  • Full root access
  • Current plan, bandwidth, discount, and included backup/snapshot terms apply; verify details at checkout before purchase.

Recommended Architecture

The VPS is the runtime layer. You connect over SSH, configure PicoClaw, and control logs, state, and access. Virtarix does not supply model keys or operate the PicoClaw layer.

You (Operator)

You connect over SSH and control the full workflow, configuration, security, and updates.

Virtarix VPS

Provides the persistent server with storage, networking, root access, snapshots, and backups.

PicoClaw Runtime

PicoClaw runtime layer and processes running on the VPS.

External Services

API and model providers, repositories, tools, and integrations that you connect and manage.

Step-by-Step Setup Flow

Follow this sequence as a practical deployment checklist, but confirm PicoClaw-specific versions, installer flags, service commands, checksums, and security notes against current official documentation before production-style use.

Deploy and connect

Prepare the VPS, connect over SSH, and create a clean workspace before installing PicoClaw-specific dependencies.

Deploy the VPS

Choose Ubuntu, Debian, or another Linux distribution supported by the PicoClaw release and install path you select. The package commands below are Debian/Ubuntu examples. Select the location closest to the user, app, API provider, or team where practical, and start with enough CPU, RAM, and storage for persistent background work.

Connect over SSH

Connect to the VPS over SSH using the server IP and the approved root or bootstrap login.

ssh root@YOUR_SERVER_IP

Update the server

Update package metadata and apply security updates before installing PicoClaw dependencies.

sudo apt update
sudo apt upgrade -y

Create a non-root user where practical

Create a dedicated non-root deployment user for day-to-day project work, then verify that user can connect by SSH and run sudo before disabling root or password login. Reconnect as the deployment user before installing or configuring the agent when your selected runtime path stores user-scoped configuration.

# Create a dedicated non-root user for day-to-day project work
adduser deploy
usermod -aG sudo deploy

Prepare a private runtime workspace

Create one directory tree for PicoClaw config examples, working files, logs, and backups. Keep secrets out of shell history and commit only templates, not real keys.

APP_HOME="$HOME/self-host-picoclaw-on-vps-runtime"
mkdir -p "$APP_HOME/config" "$APP_HOME/workspace" "$APP_HOME/logs" "$APP_HOME/backups"
chmod 700 "$APP_HOME" "$APP_HOME/config" "$APP_HOME/workspace" "$APP_HOME/logs" "$APP_HOME/backups"
printf '%s\n' "# copy the official template, then add real provider keys privately" > "$APP_HOME/config/env.example"
chmod 600 "$APP_HOME/config/env.example"

Install and configure

Install base packages, confirm the current stable release and VPS architecture, follow the selected upstream install path, and configure runtime settings.

Install base dependencies

Install the baseline packages needed for downloads, Git workflows, certificates, and archive handling.

sudo apt install -y git curl wget unzip ca-certificates gnupg

Install runtime dependencies

The official PicoClaw repository describes PicoClaw as a Go-based project, and the installation docs list Go 1.21+ for source builds. For Web UI builds, confirm the current Go, Node.js, and pnpm requirements before installing build tooling on the VPS. If you use the precompiled binary path, keep the server dependencies minimal and avoid installing unnecessary build tools.

Confirm VPS architecture and release channel

Use the latest stable release unless you intentionally need a nightly or pre-release build. Match the release asset to the VPS CPU architecture before downloading.

uname -m
# x86_64  -> picoclaw_Linux_x86_64.tar.gz
# aarch64 -> picoclaw_Linux_arm64.tar.gz

Install or clone PicoClaw

Use the official PicoClaw download, release, source, or documented container path you selected. Match the release asset to the VPS CPU architecture, avoid unofficial mirrors, and compare checksums when provided.

# Option A: precompiled x86_64 Linux binary example only.
# Choose the matching release asset for your VPS architecture.
PICOCLAW_ASSET="picoclaw_Linux_x86_64.tar.gz"
curl -fL "https://github.com/sipeed/picoclaw/releases/latest/download/${PICOCLAW_ASSET}" -o "${PICOCLAW_ASSET}"
tar -xzf "${PICOCLAW_ASSET}"
chmod +x ./picoclaw
./picoclaw version
./picoclaw onboard

# Option B: source build path for development or auditing.
# Run these only if you selected the source path.
# git clone https://github.com/sipeed/picoclaw.git
# cd picoclaw
# make deps
# make build

# For launcher/Web UI builds, also follow current upstream frontend steps,
# such as installing web/frontend dependencies and running make build-launcher.

Configure PicoClaw settings

Use the configuration files created by onboarding as the authority. Keep provider keys and channel credentials in the security/configuration files expected by the current release.

# If you installed PicoClaw into PATH, use picoclaw instead of ./picoclaw
./picoclaw onboard

# Or initialize with credential encryption where it fits your workflow
# ./picoclaw onboard --enc

nano ~/.picoclaw/config.json
./picoclaw status

Start PicoClaw

Start with the command path you verified during onboarding. Keep gateway or Web UI access local while testing, then expose only after reviewing authentication and firewall rules.

# If you installed PicoClaw into PATH, use picoclaw instead of ./picoclaw
./picoclaw agent -m "test runtime"
./picoclaw agent
./picoclaw gateway

Run, secure, and maintain

Keep the selected PicoClaw runtime observable, lock down access, test the setup, and plan ongoing maintenance.

Keep It Running

Use the process-management path that matches the deployment you selected, and place only the reviewed PicoClaw command behind systemd, supervisor, tmux, Docker Compose, or another controlled manager.

# Binary or source path: verify the command before adding service supervision
./picoclaw status
./picoclaw gateway

# Docker path from the official installation docs.
# Run these only if you selected the Docker path.
# git clone https://github.com/sipeed/picoclaw.git
# cd picoclaw
# docker compose -f docker/docker-compose.yml --profile gateway up
# vim docker/data/config.json
# docker compose -f docker/docker-compose.yml --profile gateway up -d
# docker compose -f docker/docker-compose.yml logs -f picoclaw-gateway

Secure the VPS

Use SSH keys where possible, restrict password login if appropriate, enable a firewall, expose only the ports PicoClaw actually needs, and protect PicoClaw config/security files.

sudo ufw allow OpenSSH
sudo ufw enable
sudo ufw status verbose

Test the Setup

Confirm PicoClaw starts, inspect logs, test provider authentication, test any webhook or interface the setup uses, restart the VPS, and confirm the service returns cleanly.

./picoclaw status
df -h
free -h
ss -tulpn

Maintain It Over Time

Review PicoClaw logs, rotate keys when needed, monitor disk usage, monitor RAM and CPU usage, update framework dependencies, snapshot before upgrades, and keep rollback notes. Re-check upstream release notes before every major update, especially while PicoClaw remains before v1.0.

Why PicoClaw Benefits from a VPS

PicoClaw is positioned as lightweight, but a small footprint still benefits from server uptime, SSH access, logs, secure configuration files, and a controlled place to run background work.

01

Lightweight always-on runtime

Keep PicoClaw available on a small server without tying background work to a local desktop session.

02

Minimal dependency surface

Use a narrow VPS setup with only the packages, ports, repositories, and credentials the experiment actually needs.

03

Server-side logs and rollback notes

Keep process output, failed starts, update notes, environment files, and rollback steps in one place.

04

Early-stage caution

Keep the first server narrow: one user, one small set of integrations, a firewall, limited ports, and clear logs. Upstream notes describe PicoClaw as early rapid development and warn against production deployment before v1.0, so keep production-suitability language aligned with current official documentation.

Security Basics for PicoClaw on a VPS

Privileged runtime

The server can contain binaries, config files, gateway experiments, credentials, logs, and release-change notes. Harden it before any production-style use.

Troubleshooting

Common setup problems to check before blaming the VPS or framework.

SSH issues

SSH connection refused

Server firewall, wrong IP, or SSH service unavailable Confirm the VPS is running, check the IP, and verify port 22 or your configured SSH port.

Permission denied over SSH

Wrong key, wrong user, or disabled login method Check ~/.ssh/authorized_keys, user permissions, and your SSH config.

Dependency and runtime issues

Missing dependencies

Base packages or runtime packages were not installed Re-run the dependency step and compare runtime versions with official PicoClaw docs.

Go, Node.js, or pnpm mismatch

The selected PicoClaw build path expects a different runtime version Use the version manager or package source recommended by upstream docs.

Docker and process issues

Docker service not running

Docker daemon stopped or not installed This only applies if you selected the PicoClaw Docker path; start Docker and inspect logs for the documented PicoClaw Compose file and data directory.

Process stops after logout

PicoClaw gateway or agent was started from an interactive shell Verify the exact picoclaw gateway or agent command first, then run it through systemd, supervisor, tmux, or the documented Docker path.

Port and firewall issues

PicoClaw service, gateway, webhook, or supporting tool port already in use

A selected PicoClaw service, gateway, webhook, or supporting tool is bound to a port already used by another process Run ss -tulpn and move one service to a different port.

Firewall blocking picoclaw service, gateway, webhook, or supporting tool access

A required PicoClaw service, gateway, webhook, or supporting tool port is not open Open only the required port and keep all other ports restricted.

Environment and API key issues

Missing configuration or credentials

Configuration is absent or incomplete Compare the generated configuration with the selected deployment path and add only the secrets and paths required.

Invalid API key or provider error

Key is wrong, expired, or lacks access Rotate the key through the provider and update the server configuration.

Disk and memory issues

Disk space issues

Logs, caches, or repositories grew over time Check df -h, rotate logs, clean caches, and scale storage if needed.

High memory usage

Too many gateway sessions, model calls, or background tasks Reduce concurrency, inspect process memory, review logs, and scale the VPS if the workload is valid.

When This Setup Is Not Necessary

Local testing is enough

You may not need a VPS if you are only testing PicoClaw locally, working from one private machine, reviewing a small repository, or experimenting without persistent SSH access.

Server management may be unnecessary

This setup is not ideal if you do not want to manage Linux updates, SSH access, firewall rules, disk usage, credentials, or repository permissions yourself.

Use a VPS for persistent remote state

Use a VPS when the workspace, runtime state, logs, tools, and assistant workflow should stay available in a controlled remote environment.

Ready to run PicoClaw on an always-on VPS?

Deploy a self-managed PicoClaw VPS and use this guide as your review checklist while you prepare the setup.

FAQ

Can I run PicoClaw on a VPS?

Yes for testing and self-managed deployments when the release supports your Linux distribution and runtime path. Use current official documentation, and avoid production use until upstream guidance supports it.

Do I need a GPU VPS for PicoClaw?

Not for the VPS runtime pattern described here. This PicoClaw guide focuses on the runtime, provider access, channel configuration, gateway logs, and lightweight server-side tasks; verify separate hardware needs if you plan local model inference or vision-heavy workloads.

Does Virtarix provide API keys or model access?

No. Bring your own provider accounts, credentials, API keys, model access, repositories, and framework configuration.

What VPS size should I use for PicoClaw?

Start with the recommended Virtarix S plan shown on this page for a practical test deployment, then scale after measuring CPU, RAM, storage, process count, gateway activity, and build requirements.

Can PicoClaw keep running without my local machine?

Yes, if PicoClaw is run as a server-side process using a documented service or process-management method. The VPS keeps the PicoClaw runtime, configuration, logs, gateway process, and provider credentials separate from your local desktop session.

Can I use Docker for this setup?

Use Docker when the official PicoClaw documentation supports it or your deployment design calls for it. Otherwise use the official runtime path.

Should I use PicoClaw nightly builds on a VPS?

Use stable releases for a safer VPS baseline. Use nightly or pre-release builds only when you intentionally accept instability and have a rollback snapshot.

Is Virtarix operating PicoClaw for me?

No. Virtarix provides the VPS infrastructure. You install, configure, secure, update, and operate the software you run on it.