For AI agents: The documentation index is at https://docs.digitalocean.com/llms.txt. Markdown versions of pages use the same URL with index.html.md in place of the HTML page (for example, append index.html.md to the directory path instead of opening the HTML document).

ZeroClaw is a fast, small, and fully autonomous AI assistant infrastructure built in Rust. It serves as the runtime operating system for agentic workflows — abstracting models, tools, memory, and execution so agents can be built once and run anywhere.

With a memory footprint under 5MB and cold start times under 10ms, ZeroClaw is designed for cost-efficient deployment on minimal hardware.

Features

• Lean Runtime: Single Rust binary with <5MB RAM usage and near-instant startup
• Provider Agnostic: Supports OpenAI, Anthropic, OpenRouter, Ollama, and any OpenAI-compatible endpoint
• Multi-Channel: CLI, Telegram, Discord, Slack, WhatsApp, and more
• Built-in Memory: SQLite hybrid search with vector + keyword retrieval
• Secure by Default: Gateway pairing, sandbox execution, filesystem scoping, encrypted secrets
• Fully Swappable: Every subsystem is a trait — swap providers, channels, tools, and memory with config changes

System Components

Software Included

This Marketplace listing does not include a detailed software list.

Creating an App using the Control Panel

Click the Deploy to DigitalOcean button to create a Droplet based on this 1-Click App. If you aren’t logged in, this link will prompt you to log in with your DigitalOcean account.

Creating an App using the API

In addition to creating a Droplet from the ZeroClaw 1-Click App using the control panel, you can also use the DigitalOcean API. As an example, to create a 4GB ZeroClaw Droplet in the SFO2 region, you can use the following curl command. You need to either save your API access token to an environment variable or substitute it in the command below.

curl -X POST -H 'Content-Type: application/json' \
         -H 'Authorization: Bearer '$TOKEN'' -d \
        '{"name":"choose_a_name","region":"sfo2","size":"s-2vcpu-4gb","image":"zeroclaw"}' \
        "https://api.digitalocean.com/v2/droplets"

Getting Started After Deploying ZeroClaw

1. Create a Droplet using this 1-Click image

2. Configure inference using one of:- Set MODEL_ACCESS_KEY (and optional INFERENCE_MODEL) as droplet environment variables at create time — Serverless Inference is applied on first boot with no wizard

   • Edit /opt/zeroclaw.env, then reboot or run sudo /opt/apply-inference-from-env.sh
   • SSH in and complete the interactive setup wizard on first login

3. Access the gateway at https://your-droplet-ip

DigitalOcean Serverless Inference

Serverless Inference uses a single model access key at https://inference.do-ai.run/v1. The default model is Kimi K3 (kimi-k3).

Supported model IDs include kimi-k3, minimax-m2.5, glm-5.3, and anthropic-claude-4.5-sonnet. During interactive setup you can pick a model from the menu. Re-run sudo /etc/setup_wizard.sh to switch providers, or edit default_model in /home/zeroclaw/.zeroclaw/config.toml.

Managing ZeroClaw

Service Control

# Restart the service
systemctl restart zeroclaw

# Check service status
systemctl status zeroclaw

# View logs
journalctl -u zeroclaw -f

Helper Scripts

# Restart with status check
/opt/restart-zeroclaw.sh

# Show status and version
/opt/status-zeroclaw.sh

# Update to latest version
sudo /opt/update-zeroclaw.sh

# Configure custom domain with TLS
sudo /opt/setup-zeroclaw-domain.sh

# Run CLI commands
/opt/zeroclaw-cli.sh status
/opt/zeroclaw-cli.sh doctor    
/opt/zeroclaw-cli.sh gateway get-paircode --new
/opt/zeroclaw-cli.sh agent -a assistant -m "Hello"

Reconfigure Provider

sudo /etc/setup_wizard.sh

Custom Domain with HTTPS

Point your domain’s DNS to your Droplet’s IP, then run:

sudo /opt/setup-zeroclaw-domain.sh

This configures Caddy with automatic Let’s Encrypt TLS certificates.

Update ZeroClaw

sudo /opt/update-zeroclaw.sh

This downloads the latest release binary from GitHub and restarts the service.

Configuration

The main configuration file is located at /home/zeroclaw/.zeroclaw/config.toml. See the ZeroClaw documentation for all configuration options.

Resources

• ZeroClaw GitHub
• ZeroClaw Documentation
• ZeroClaw Releases