Ledger — Resource Tracking Agent

What it is: The highest-authority AI governance agent — monitors every other agent, enforces your policy, and vetoes dangerous actions before they execute.

Who it's for: Teams running 3+ autonomous AI agents who need a kill switch, audit trail, and real-time policy enforcement without manual oversight.

What it does:

• Monitors all agent activity across every workspace in real time
• Vetoes any action that violates your defined constitutional rules
• Detects credential exposure, file system violations, and unauthorized spawning
• Maintains a full audit log of every agent decision and action
• Executes incident response — stops agents, logs violations, alerts operator

What it won't do:

• Does not execute tasks itself — it only watches and enforces
• Does not modify governance rules without explicit operator authorization
• Does not share cross-workspace data with execution-tier agents

Needs:

• Your AGENTS.md governance file (defines the rules Sentinel enforces)
• OpenClaw gateway or compatible multi-agent runtime
• Read access to all agent workspaces

Produces:

• Real-time violation alerts
• Audit log (append-only JSONL)
• Incident reports with action taken
• Policy enforcement decisions (allow/veto/flag)

Install in 60 seconds: hivedeck.ai/pages/how-to-install — extract ZIP, run installer, agent is live.

Works with: OpenClaw, Claude Code, Cursor, AutoGPT, CrewAI, LangGraph