Runtime + Control Plane

OpenClaw Runs Your Agents.
ClawButler Makes Them Safe.

OpenClaw is the runtime. ClawButler is the control plane. We don't build Agents — we make your existing Agents visible, controllable, and compliant.

Why Now

The Governance Gap Is Real

49.3%
of enterprises have 10+ Agents deployed — IDC
512
vulnerabilities found in OpenClaw — Kaspersky audit
3.5x
cost overhead in multi-Agent coordination vs single-Agent
<10%
of teams successfully scale beyond one Agent — IDC
1Visibility

Your Agents are running. But can you see them?

You have six Agents deployed. One is healthy, one is pending approval, one went offline four minutes ago. Right now, you have no way to know this without SSH-ing into the box and reading logs. ClawButler changes that in one connection.

Connect your OpenClaw instance once. Every Agent is auto-discovered. Dashboard, topology map, live activity stream, and session monitor — all real-time, all in one place.

clawbutler.cc/dashboard
research-bot
healthy
code-agent
approval pending
data-sync
healthy
monitor
healthy
translator
offline 4m
scheduler
healthy
Live Activity
14:32research-bottool_call: web_search
14:31code-agentapproval_required: file_write
14:28translatordisconnected: timeout
2Governance

Your Agent just tried to delete your staging data.

OpenClaw has no authentication by default. 512 vulnerabilities found by Kaspersky. 335 malicious Skills confirmed on ClawHub. Once an Agent gets tool access, any allowed sender can trigger tool calls within its permissions — including destructive ones.

Every high-risk operation goes through HITL Approval with full context and impact assessment. One-click approve or deny. Kill Switch for emergencies. Every action enters an immutable audit trail.

clawbutler.cc/approvals
Approval Required
HIGH RISK
code-agent wants to execute:
shell_exec: rm -rf /data/staging/*
Impact: destructive file operation on staging data directory
Kill Switch
All 6 agents active. Emergency shutdown ready.
3Security

Is your OpenClaw gateway actually secure?

Kaspersky found 512 vulnerabilities in OpenClaw. Censys discovered 21,639 instances exposed on the public internet. 335 malicious Skills on ClawHub. But most operators don't know if their own gateway has auth enabled, if transport is encrypted, or if high-risk tools are wide open — until it's too late.

ClawButler scans your OpenClaw configuration against the latest known vulnerabilities and security best practices. Transport encryption, authentication, network exposure, tool risk levels, malicious Skill detection — checked on first connection and continuously via nightly trust audits.

clawbutler.cc/health-check
Security Scan2 WARNINGS
Transport Encryptionwss:// (TLS)
Operator AuthenticationBearer token present
Network ExposurePublic endpoint detected
Tool Permissions3 high-risk tools enabled
Malicious SkillsNo known threats
Gateway Auth Modeopen (no password)
Trust VerdictREVIEW NEEDED
Nightly audit: 2 issues found. Last scan: 6h ago.
4Cost

Last month cost $400. But which Agent spent it?

OpenClaw's usage.cost API only reads the main Agent's sessions — a hardcoded limitation. Multi-Agent coordination burns 3.5x more tokens than single-Agent. Without per-Agent attribution and spend caps, costs spiral silently.

Per-Agent cost breakdown via sessions.usage. Budget circuit breakers that auto-alert or auto-halt when thresholds are reached. Root cause tree drills down to Agent, model, and time period.

clawbutler.cc/cost
Today
$17.85
This Week
$89.20
Budget Left
$110.80
Cost by Agent
research-bot$12.40
code-agent$3.20
translator$1.80
data-sync$0.45
5Config Safety

You changed one config line. Or your AI did. Now nothing works.

OpenClaw config is powerful but fragile — the model field can be a string or a dict, methods split into gateway-global vs per-agent, resolved and config mean different things. Whether you broke it manually or an AI assistant changed something wrong, there's no native rollback.

Two safety nets: Every Agent config change creates an immutable snapshot — with semantic diff, rollback preview, drift detection, and auto-save of current state before restoring. At the gateway level, encrypted backup packages export your entire setup for full or scoped restore, with preview before apply.

clawbutler.cc/config/diff
Config Diff: v12 → v132 changes
- model: "anthropic/claude-sonnet-4-20250514"
+ model: "anthropic/claude-sonnet-4-6"
- maxTokens: 4096
+ maxTokens: 8192
6Templates

New Agent, same copy-paste. What could go wrong?

Every new Agent starts from scratch or a hastily copied config. Different environments drift apart silently. There's no standard way to validate before deploying, and no automatic recovery when things break.

Verified Templates with type-safe variables and compatibility validation. Preview exactly what will change before deploying. If deployment fails, automatic rollback kicks in.

clawbutler.cc/templates
Research Agent
Official
Code Review Bot
Community
Data Pipeline
Official
Support Agent
Community
Deploy PreviewCompatible
Variables: model=claude-sonnet-4-6, maxTokens=4096, tools=3
7Automation

It's 3 AM. Who's watching your Agents?

Health checks, cost reports, config audits, incident response — all done by hand, all during business hours. At night and on weekends, your Agents run unsupervised.

Runbooks turn routine operations into observable, auditable workflows with built-in approval gates. Trigger by schedule, webhook, or event. Every step logged, every failure alerted.

clawbutler.cc/runbooks/daily-health
Daily Health CheckRunning
Check all agent health2s
Sync cost from OpenClaw5s
Detect config drift...
Generate daily report
Send to Slack
Trigger: every day at 08:00 UTC · Last run: 23h ago

Four Platforms, One Control Plane

Govern from Anywhere

Web Dashboard
Deep management, config, analytics — 36+ pages
CLI
Scriptable automation, AI-native ops — 60+ commands
Mobile
On-call approvals, emergency response — iOS & Android
MCP Server
AI assistants operate governance directly — 40+ tools

Design Philosophy

What ClawButler Won't Do

ClawButler is a control plane for OpenClaw, not a fork of it. We choose to govern, not to replace. These are deliberate design boundaries.

1

Fix OpenClaw's cron scheduler

We detect anomalies and offer Runbook migration as a better alternative — but we won't patch OpenClaw's internal scheduler. That's their runtime.

2

Recover lost session context

We trace the impact via Sessions and Audit so you know exactly what was lost — but we won't reconstruct OpenClaw's compaction output. That's their data layer.

3

Correct memory state semantics

Memory Browser gives you visibility into the current state — but we won't override OpenClaw's memory subsystem behavior. That's their internal contract.

4

Patch webchat or pairing auth

Connector diagnostics help you pinpoint issues faster — but we won't modify OpenClaw's frontend or token flow. That's their auth implementation.

5

Clean up orphan processes

Health Check surfaces process anomalies so you can act quickly — but we won't reach into OpenClaw's process tree. That's their runtime responsibility.

Ready to take control?

Start with managed Cloud, pair a runtime host, or self-host for full data control.

Self-Hosted Community: all features, free forever. Cloud Free: no credit card required.

Why ClawButler — The Governance Layer for OpenClaw Agents