Stop Fighting Config Files
Get OpenClaw running in one session. Install Docker, paste one bootstrap command, and the Zedly setup agent configures LLM providers, installs plugins, verifies your gateway, and gets your first agent running — all inside a pre-built container on your machine.
Works on macOS, Windows, and Linux. For anyone who wants OpenClaw working without the headaches.
How It All Fits Together
One machine, full isolation, GPU-accelerated local models, cloud AI, and real-time monitoring.
Three Steps. One Session. Done.
No screen sharing. No ticket queues. Direct access to your OpenClaw instance.
Install Docker, Paste One Command
OrbStack on Mac (recommended) or Docker Desktop / Docker Engine. Copy the one-line bootstrap command from your Setup dashboard; it pulls the pre-built Zedly OpenClaw container, injects your session key, and opens a secure outbound tunnel — all in one go. docker stop ends the session.
Agent-Assisted Setup
LLM providers, model routing, plugin installation, gateway verification, and first agent test — all handled.
You're Live
Working OpenClaw instance with your preferred models, plugins installed, config backed up. Session log exported.
What Gets Configured
Everything you need to go from installed to productive.
LLM Provider Setup
API key configuration for OpenAI, Anthropic, Google, Groq, Ollama, or any provider OpenClaw supports. Verified working before we move on.
Model Routing
Configure which model handles which task. Frontier models for reasoning, budget models for extraction. Optimized for your workflow and cost target.
Shield Installation
Install and configure Zedly Shield for PII redaction, API key detection, content deny lists, and audit logging. Protection from the start.
First Agent Test Run
Your first agent runs successfully before the session ends. We verify tool calls, model responses, and output quality live.
Cron & Scheduling
Set up scheduled agent runs for recurring workflows. Cron configuration, log rotation, and error monitoring handled.
Config Backup
Your working configuration is backed up locally. If an OpenClaw update breaks something, you have a known-good state to restore.
Use Cases
Pre-built workflows you can deploy in minutes. Cold email outreach, lead enrichment, and more. Browse use cases
Docker + Local LLM
One-command install via Docker (OrbStack on Mac, Docker Desktop on Windows). Run multiple isolated instances — keep one stable, experiment on another. Install Ollama on bare metal for full GPU/Metal acceleration, and all containers share the local model automatically.
Outlook Attachment Drop (Mac)
Let OpenClaw process files emailed to your Outlook inbox. A one-command Mac installer adds a scheduled AppleScript that saves attachments from a named Outlook folder straight into your container — no cloud auth, no Azure app, no OpenClaw image rebuild. Works with Microsoft 365 work accounts.
Your Machine, Your Control
A signed container, an outbound-only tunnel, and docker stop — you decide when access starts and stops.
Local Container
OpenClaw, Shield, and the tunnel all run inside a pinned, signed container pulled from GitHub Container Registry. Everything executes on your hardware — no files are copied to Zedly.
Per-Session Outbound Tunnel
The container initiates an outbound connection to Zedly — no inbound ports on your host. The gateway binds to localhost only, and each instance gets its own local port so multiple OpenClaws can run side-by-side. docker stop ends the session instantly.
Per-Session Keys + Full Audit Log
Each session generates a unique ed25519 SSH key that the bootstrap script injects into the container and that auto-revokes on the server when the session ends. Every command the setup agent runs is logged to an exportable per-session audit trail.
Nothing Installed On Your Host
No OpenClaw, Node, or OpenSSH server on your base OS. Remove the container cleanly at any time with docker rm — and your host OS is untouched.
Deploy Pre-Built Workflows
Once configured, launch guided use cases directly through your setup session. Each workflow includes PII protection via Zedly Shield, agent memory that learns over time, and step-by-step setup.
Intelligent Email Triage
Connect your Gmail or IMAP inbox. The agent scans, classifies, drafts replies in your writing style, sends Telegram alerts for VIPs, and compiles a daily digest. Gets smarter over weeks via QMD memory and Dreaming.
~25 min setupCold Email Outreach Engine
Full prospecting pipeline: find leads, verify emails with Hunter, draft personalized messages, authenticate your domain (SPF/DKIM/DMARC), and send through Google Workspace with a 5-agent OpenClaw workflow.
~30 min setupVibe Coding — DevOps from Your Phone
Ship code, review PRs, and deploy from Telegram with a 4-agent team (planner, coder, tester, reviewer). Shield auto-redacts secrets and gates destructive commands. QMD + Dreaming learns your codebase conventions over weeks.
~35 min setupMore coming soon
Lead enrichment, competitive monitoring, document processing, and more.
Pick Your Lane
Get OpenClaw configured in one session, then keep it protected, monitored, and stocked with vetted workflows - without hiring an MLOps engineer.
Solo
- Up to 2 OpenClaw instances
- Shield daemon + cloud dashboard
- 1 standard workflow included
- Config backups + update notifications
- Email support, 48h response
- Buy extra workflows a la carte ($29 each)
Consultant
- Up to 15 instances (+$5/mo per extra)
- Shield on every instance with policy sync
- 3 workflows included across all instances
- Multi-client fleet dashboard
- Unlimited self-serve installs and re-configs
- Priority email + chat, 24h response
Enterprise
- Up to 250 instances under one fleet dashboard
- Shield with custom policy packs
- All marketplace workflows included
- Dedicated setup engineer for rollout
- Dedicated support engineer, 4h SLA
- SSO, audit log export, SOC 2 artifacts
Frequently Asked Questions
curl … | bash on macOS/Linux, irm … | iex in PowerShell on Windows). That single command pulls the latest Zedly OpenClaw image, creates the container, injects the session's SSH key, and opens a secure outbound tunnel back to Zedly — if the container already exists it just reconnects. Once connected, open the localhost:<port> link shown in the dashboard for the OpenClaw gateway UI (each instance gets its own host port so you can run multiple OpenClaws side-by-side). The Zedly setup agent then configures LLM providers, installs plugins, and verifies your first agent through the Setup chat. No SSH server on your host, nothing permanent installed, and docker stop ends the session at any time.localhost on your machine — each instance gets its own local port (never exposed to the internet). Every command the setup agent runs is logged to a per-session audit trail you can export. docker stop or docker rm cleanly disconnects and removes the container.~/.zedly/containers/<instance>/.openclaw and ~/.codex), so the container can be replaced without touching your data. Want to test a new OpenClaw release without risking your main setup? Spin up a second instance from the dashboard — each instance gets its own config volume, so you can upgrade one while keeping the other on the stable version.Questions or feedback?
Tell us what you need, what's missing, or what would make this a buy. We read everything.
Thanks — we got it.
We'll reply to your email within 1 business day. In the meantime, check out the setup assistant guide.
No spam. Straight to the team.
Get OpenClaw Running. Today.
Start a 7-day Solo trial or pick the plan that fits. Stop fighting config files.