Config & profiles per role.
A single openclaw.json doesn't scale for a productive team. We split config into profiles per role, channel and tenant — cleanly versioned.
Why this matters right now.
OpenClaw loads a global openclaw.json from your home folder. Once you have several roles, channels or tenants, the file becomes messy, secrets leak in plaintext, and nobody knows which config is currently active.
Here's how we do it.
We split config into profiles (sales, support, operations …), keep secrets out via macOS Keychain or systemd credentials, document model routing per provider and version everything in a private Git repo.
The full package.
Role profiles
Sales, marketing, operations, IT — each profile has its own skills, channels, allowlists and models.
Model routing
Fast models for triage (Haiku, gpt-4o-mini), strong ones for drafts (Sonnet, gpt-5), local for sensitive data (Llama 3.3 via Ollama).
Secrets
API keys not in plaintext: macOS Keychain, systemd credentials, 1Password CLI or Vault — referenced cleanly.
Versioned
Config in a private Git repo, with pull requests for every change — auditable, rollback-able.
Limits
Token budgets, rate limits per skill and channel, automatic escalation on overrun.
Override path
Individual users can set override defaults in their own sub-profiles without breaking the team standard.
From first call to a productive OpenClaw workflow.
-
01
Analyse
30-min check + process map. We pinpoint the 3 workflows where OpenClaw saves time fastest, and which channels are mandatory.
-
02
Setup
Daemon, channels, skills, MCP, allowlists, requireMention, Tailscale and the live dashboard configured cleanly and live.
-
03
Training
Your team works on real tasks: WhatsApp inbox triage, weekly Slack-DM reports, voice-memo-to-CRM, skill maintenance.
-
04
Operations
calver updates, skill extensions, channel care, security reviews, backups and an emergency off-switch — so OpenClaw doesn't fade out.
Three entry points. One outcome: OpenClaw that works.
Starter
For small teams and 2–3 workflows on one channel
+ from €180 / month maintenance & care
- OpenClaw daemon installed, hardened, monitorable (launchd/systemd)
- 1 messaging channel (WhatsApp, Telegram, Slack or iMessage) cleanly paired
- 2–3 productive skills (inbox triage, research or reporting)
- 2 MCP tool integrations (e.g. Drive, Notion, Slack, CRM, calendar)
- Allowlists, requireMention, GDPR defaults and backup plan
- 2-hour intensive training + 30 days of care
Business
★ Most pickedFor SMBs with several roles, channels and tool integrations
+ from €490 / month maintenance & care
- OpenClaw rollout for up to 25 users with Tailscale mesh
- 4–6 channels in parallel (WhatsApp, Slack, Telegram, Teams, voice …)
- 6 team- or role-specific skills (sales, marketing, operations …)
- 5 MCP integrations + voice (STT/TTS) configured
- Half-day workshop on-site or remote
- Security hardening incl. CVE protection and GDPR docs
Enterprise
For sensitive data, compliance and fleet rollout
+ from €1,290 / month maintenance & care
- Enterprise setup with central config, fleet auth and audit trail
- Custom MCP server or internal tool adapters incl. code review
- 10+ skills, departmental playbooks, train-the-trainer programme
- Voice, canvas, Tailscale, backup and SIEM integration
- Governance documentation for ISMS, GDPR and ISO 27001
- Monthly security and optimisation reviews
These pair well with this.
OpenClaw Workshop
One day with your team: install daemon, pair channels, curate skills, scope MCP, harden defaults — together.
Learn moreAI Operating System
OpenClaw as the central work layer for inbox, offers, reports, research, calendar and CRM.
Learn moreDaemon Setup
launchd, systemd, Node 24, openclaw onboard, clean restart paths — observable, restartable, monitored.
Learn moreStill open questions?
Write us at hello@openclaw-os.com or book a call directly. We'll take the time.
Does OpenClaw switch profiles automatically?
Can I run multiple LLM providers?
What if my team starts hand-rolling configs?
What does a complete OpenClaw setup cost?
Is OpenClaw only useful for engineers?
Which channels make sense?
Book a call.
30 minutes that pay off.
Pick a slot — we confirm automatically and send you the Google Meet link.