AI agents that run on a schedule to automate recurring work
The approval layer for AI agents
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
US
Pricing model
Not given
Freemium
Pricing
Free plan: $0 per month with up to 3 agents, runs as often as every hour, 200 run minutes each month, runs up to 10 minutes, 1 active run at a time. Pro plan: $25 per month ($20 per month when billed annually) with no fixed agent limit, runs as often as every 5 minutes, no fixed monthly run-minute l
Open Source: free and self-hosted. Free: $0/month hosted plan with up to 5 members. Scale: $20 per user per month. Enterprise: Custom annual contract.
Key features
Create agents with Markdown descriptions
Run agents on custom schedules from every 5 minutes to once a week
Agents keep memory and self-improve between runs
Connect any tool with an API, MCP, or CLI
Sandbox environment with package installation
MCP server for ChatGPT and Claude integration
Live output and run history
Support for subscriptions and API keys
Tool call interception for all agent frameworks
Automatic approval rules to prevent fatigue
AI judge for complex rule evaluation
Works with LangGraph, CrewAI, Mastra, Claude Agent SDK and more
Open Agent Approval Protocol for framework independence
Self-hosted or cloud-hosted deployment options
Custom permission policies and organization controls
What makes it different
Agents remember previous runs and continuously self-improve
Works with any tool, API, or skill via integrations
Control agents directly from ChatGPT and Claude
Fresh sandbox for each run with automatic package installation
Framework-agnostic: works with any AI agent through the open Agent Approval Protocol
No vendor lock-in: open source spec and SDKs let you swap providers without rewriting agents
Comprehensive audit trail for accountability and compliance
Meets reviewers where they work with multi-platform notifications
Policy-based routing to eliminate approval bottlenecks
Cronloop
withHuman