██████╗ ██╗ ██╗███╗ ██╗██╗ ██╗ ██████╗ ██████╗ ██╔══██╗██║ ██║████╗ ██║██║ ██╔╝██╔════╝ ██╔═══██╗ ██████╔╝██║ ██║██╔██╗ ██║█████╔╝ ██║ ███╗██║ ██║ ██╔═══╝ ██║ ██║██║╚██╗██║██╔═██╗ ██║ ██║██║ ██║ ██║ ╚██████╔╝██║ ╚████║██║ ██╗╚██████╔╝╚██████╔╝ ╚═╝ ╚═════╝ ╚═╝ ╚═══╝╚═╝ ╚═╝ ╚═════╝ ╚═════╝
_
Every AI action gets a receipt.
Dashcam for AI coding. Append-only, Ed25519-signed, RFC 3161 timestamped.
▼ ▼▼▼ ▼▼▼▼▼scroll down
░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░
// Why I built this
I've been using Claude Code daily since January 2025. After 25,000+ AI actions, I realized I had zero proof of what actually happened. The AI's own logs? It can edit those. Git history? Doesn't capture the thinking process.
I wanted something that works like a dashcam — always recording, can't be tampered with, and there when you need it.
If you use Claude Code or Cursor for client work, team projects, or anything where you need to show what your AI actually did — this is for you.
░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░
// Quick Start
░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░
// Three Trust Layers
Each layer adds a guarantee the layer below cannot provide.
Merkle Tree
Proves this event is in the tree, and the tree is append-only. RFC 6962.
Ed25519 Signature
Proves this kernel instance signed this checkpoint. RFC 8032.
TSA Timestamp
Proves this checkpoint existed before time T. You cannot backdate it. RFC 3161.
░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░
// Supported Tools
░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░
ENTER THE LAB
See what's being built with PunkGo Kernel
[ PRESS START ]