toolgrep

toolgrep / AI agents & frameworks

RunVouch

Watchdog for unattended AI agents with a tamper-evident proof per run

Visit runvouch.com →DocsPricing

RunVouch monitors scheduled AI agents (Claude Code Routines, headless claude -p, OpenClaw, n8n, cron) and alerts when a run is missed, fails silently, lacks evidence of output, loops on identical tool calls, exceeds cost/token budgets, drifts from baseline, or stalls. Each finished run gets a hashed record; daily Merkle roots are chained and anchored via OpenTimestamps. Includes a CLI, Claude Code plugin, and MCP server. Self-hostable under MIT.

Category
AI agents & frameworks
Pricing
freemium
Free tier
yes
API
yes
MCP server
yes
SDK
yes
Open source
yes

#ai-agents#monitoring#cost-caps#cron#claude-code#mcp#self-hosted#audit-trail

Listed 2026-10-28 · last verified 2026-10-28 · extracted by @cf/zai-org/glm-5.3-flash · confidence 0.95

API
curl https://toolgrep.com/api/products/runvouch