Free: $0/mo for 1 agent with scanner, approvals, kill switch, phone and Telegram alerts, and 7-day history. Pro: $24.99/mo for up to 5 agents with learned autonomy, Time Machine, data-leak tripwire, vault, and unlimited history. Team: $79.99/mo for unlimited agents with everything in Pro plus priori
Free. The code is on GitHub under Apache 2.0. A future hosted team office feature will be paid.
Key features
Skill scanner for hidden instructions in documentation
Encrypted vault for secrets kept away from agent context
Kill switch for instant agent stopping
Rewind time machine to walk back agent actions
Data-leak tripwire for PII and secrets detection
Live operations dashboard monitoring all agents
Phone and Telegram alerts for held and blocked actions
Multi-agent monitoring from a single screen
Real-time status visualization with color-coded states
Tool approval and command authorization
Team workflows with task handoffs
In-conversation steering without window switching
System notifications for approval requests
Local-only architecture with no data leaving machine
Auto-deny protection for undecided requests
Integration with existing Claude subscription
What makes it different
Runtime gate checks actions before they execute, not after like logs
External to agent so injected content cannot override security rules
Differentiates between reversible actions that flow immediately and irreversible ones needing approval
Catches runtime threats that static scanning misses
Built for individual developers, not enterprise
Complete local-first privacy: code and transcripts never leave your machine
No configuration or learning curve: read a room and you can run it
Works with your existing Claude Code installation and subscription
Open source under Apache 2.0 with no account required
Chloros
airoom