Open-Source OpenClaw Governance

The Governance Layer
for Your OpenClaw Agents

Not another Agent builder — the governance layer for your OpenClaw Agents. Real-time monitoring, cost tracking, human-in-the-loop approvals, and immutable audit trails.

clawbutler.cc/dashboard
Active Agents
12
Pending Approvals
3
Today's Cost
$4.28
Events (24h)
847
Live Activity
14:32research-bottool_call: web_search
14:31code-agentapproval_required: file_write
14:30data-synctask_completed: daily_report
14:28monitor-agenthealth_check: all_systems_ok
49 Features
Across 4 releases
90+ APIs
Native OpenClaw integration
99.9%
Approval chain availability
<3s P95
Approval ingestion latency

The OpenClaw Governance Gap

As your OpenClaw Agents grow in number and complexity, operators face unprecedented challenges

What did my Agent do last night?

Agents run 24/7, but you only discover incidents after damage occurs. No real-time observability.

How much did it cost?

Token costs grow exponentially with usage. Without budget circuit breakers and anomaly detection, costs spiral unchecked.

Who approves high-risk actions?

Agents autonomously call external tools and APIs. A single unauthorized operation can cause irreversible damage.

Config scattered everywhere

Agent configs, model parameters, and permission rules scattered across files and interfaces. No unified view or version control.

Comprehensive OpenClaw Governance

From visibility to actionability, from cost control to compliance — all in one place

HITL Approval

Real-time high-risk operation monitoring with rich impact assessment cards. One-click approve or deny. Default fail-closed with askFallback=deny.

Activity Feed

Real-time feed of all Agent activities. Filter by Agent, type, or time. Daily summaries keep you in the loop.

Cost Governance

Multi-dimensional cost attribution, trend analysis, budget circuit breakers, and anomaly detection. Model tiered routing for instant savings.

Agent Health + Kill Switch

Three-state health monitoring (healthy / degraded / offline) with 30-second offline alerts. Emergency kill switch with manual recovery confirmation.

Config Panorama

Zero-gap config visibility across 6 tabs — Overview, Files, Tools, Skills, Channels, Cron. Diff, versioning, and drift detection.

Audit Trail

Append-only audit log with full-text search and trace_id linking. Every operation traceable to a person.

Mobile Governance

Expo/React Native mobile app for approvals, monitoring, budgets, and kill switch workflows from anywhere.

Cron Management

Full CRUD for scheduled jobs with consecutive failure alerts and execution history. Visual scheduling configuration.

Start Governing in 3 Steps

Connect your OpenClaw instance in 5 minutes. Gain full visibility instantly.

STEP 01

Connect

Securely connect your OpenClaw instance via WebSocket. All Agents auto-discovered.

STEP 02

Observe

Real-time activity feed, cost analytics, and health monitoring — ready instantly.

STEP 03

Govern

Configure approval rules, set budget circuit breakers, define alert policies. From reactive to proactive.

Recommended Workflow

AI-Native by Design

ClawButler is a fully LLM-driven product. You can configure everything manually on the Web — but the recommended way is: let your AI read the docs, and it handles the rest.

llms.txt — AI Reads, AI Understands

Structured project docs at /llms.txt, optimized for LLM comprehension. One read, full understanding — your AI knows every API, every CLI command, every config option.

60+ CLI Commands — AI Executes

Every governance capability is a scriptable CLI command. Connect agents, set budget breakers, deploy templates, configure approval rules — your AI operates it all, autonomously.

Web Dashboard — You Observe

The Web becomes your real-time monitoring cockpit. Watch what AI configured, review audit trails, catch anomaly alerts. Intervene only when you choose to.

AI-Driven Setup
# Let your AI read the full docs
$ curl clawbutler.cc/llms-full.txt
# AI understands, then operates via CLI
$ ap connector create --name prod --url wss://gw.example.com
Connector created. 12 agents discovered.
$ ap budget create --agent-id research-bot --monthly-limit 50
Budget circuit breaker set.
$ ap approval rules update --agent-id code-agent --risk high --action require
Approval rule applied.
You just watch on the Web dashboard.

Update Log

What we shipped — and what it enables you to do

v1Released
V1 Core

Agent auto-discovery, HITL approvals, live activity feed, cost tracking with budget breakers, audit trail, kill switch

v2Released
V2 Platform

Config Safety V2 (diff + drift + rollback), Templates, Runbooks, CLI (60+ commands), Federation, One-click install

v2.5Released
V2.5 Security

Trusted Change Control, supply chain scanning, per-agent cost accuracy, idempotency, edge agent V2

v3Latest
V3 Orchestration

Workflow orchestration + topology DAG, session monitor, approval bridge, zero-spinner performance, 28-page user manual

Ready to govern your OpenClaw Agents?

Start free, deploy in 5 minutes

Home