Proof of what an AI agent was allowed to do, and what it then did
Stage
Not given
Startup
Founded
Not given
2026
Based in
Not given
Not given
Pricing model
Freemium
Open source
Pricing
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
Not given
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
Signed permissions with passkey authentication
Receipts for each agent action with signatures
Free checker tool to verify compliance
Quantum-safe signatures (Ed25519 and ML-DSA-87)
Permission narrowing for helper agents
Permission cancellation with signed acknowledgement
JavaScript and Python libraries
LangChain and Pydantic AI middleware
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
Only open-source project combining machine-checkable limits, permission narrowing for helpers, and signed permission cancellation
Built entirely from published standards with no hand-made components
Free and no dependencies, sends nothing anywhere or holds money
Distinguishes between record integrity and whether agent stayed within permission
All published versions stay available for backward compatibility
Chloros
Provared