All Features

Connect OpenClaw through secure WebSocket connectors or pair a Runtime Host to discover Hermes / Claude Code / Codex / OpenClaw instances. Selected runtimes enter the same unified registry, while OpenClaw remains the fully supported provider-native connector path.

Intercept high-risk Agent operations with configurable approval rules. Each request includes risk level, cost estimate, and impact assessment. Support for batch approve/reject, allow-once vs allow-always decisions, and optimistic concurrency on rule updates — all with full audit trail.

Multi-dimensional search across all audit events: filter by Agent, event type, risk level, trace ID, keyword, and date range. Trace chain linking reconstructs full operation histories. Config rollback with preview, and automatic PII masking on sensitive fields.

Scoped configuration snapshots (agent config, workspace bundles, bindings, dependency metadata), each independently tracking apply status. Built-in drift detection auto-flags live vs desired state divergence. Rollbacks create new versions referencing old content for forward traceability.

Emergency Agent shutdown that disables locally and propagates to OpenClaw. Three-state health monitoring (healthy / degraded / offline) with 30-second offline detection. Recovery requires explicit confirmation to prevent accidental restarts.

Automated tool inventory with periodic snapshots. Tracks tool additions, removals, and permission changes across agents. Heuristic risk scoring flags potentially dangerous tools. Change-diff detection alerts on unexpected tool mutations.

Proactive scanning of tool origins, permissions, and known vulnerabilities. Findings classified by severity (Critical / High / Medium / Low) with automated risk gating. Seed admin credential hardening included.

Live Server-Sent Events (SSE) streaming with 15-second heartbeat and cursor-based resume via Last-Event-ID. Filter by Agent, event type, risk level, and time range. Daily summary digests and long-running task progress tracking keep you informed.

Per-Agent cost attribution with breakdown by model and task type. Configurable trend analysis (daily/weekly/monthly), anomaly rate alerts, and budget circuit breakers that automatically enforce spending limits. Model routing optimizer suggests cost-saving alternatives with explainable risk assessment.

Schedule recurring agent tasks with full CRUD synced to the upstream platform. Run history with pagination, consecutive failure detection with alerts, and aggregated cron summary statistics across all agents.

Cost root cause analysis with contribution trees, per-agent reliability scoring, and value quantification.

Scheduled reports with email delivery subscriptions. On-demand generation, retry for failed deliveries, and anomaly highlights.

Template registry with type-safe variable definitions (string / number / boolean / json), pre-deploy preview of config changes and dependency impact. Post-deploy checks with severity levels run automatically. Compatibility matrix declares OpenClaw version and model capability requirements.

Multi-step operational automation centered on the OpenClaw-native path, with typed steps, approvals, verification, evidence, and a complete run lifecycle.

In-app notifications with Web Push delivery via VAPID. Subscription management with quiet hours, per-channel preferences, and cooldown controls.

Pair a machine, discover Hermes / Claude Code / Codex / OpenClaw instances, batch-add only the connectors you want, and sync attach-mode sessions for investigation. OpenClaw remains the fullest provider-native path.

Background CSV/PDF export with secure, expiring download tokens and automatic retry.

Expose ClawButler as an MCP server so Claude Code, Cursor, Windsurf, and other MCP clients can manage agents, inspect costs, run diagnostics, and trigger governance workflows directly.