Proof of what an AI agent was allowed to do, and what it then did
Your own team of AI bots, on a canvas
Stage
Startup
MVP
Founded
2026
Not given
Based in
Not given
PT
Pricing model
Open source
Free
Pricing
Not given
Free. No subscription required. Your bots run on the Claude or ChatGPT plans you already have, or on API keys you pay the providers directly. Built-in Mac voices cost nothing; other voices require your own ElevenLabs, Fish Audio or xAI key paid to those providers.
Key features
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
Run multiple AI agents simultaneously on one canvas
Granular approval controls from Ask to Full access
Schedule jobs to run on recurring dates or calendar triggers
Voice interaction with bots
Support for Claude Code, Codex, Cursor, Grok and other agents
Usage tracking and cost estimation per bot
Secure keychain-based login management
What makes it different
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
No subscription or account required; completely free to use
Work directly with your existing Claude and ChatGPT plans; no vendor lock-in
Private by default: data stays local, no analytics, keys never reach bots
Visual team dashboard showing real-time bot status at a glance