A working middleware that sits between an operator and a connected LLM and enforces a Three-Layer Alignment Stack: an Origin ground-check on every input, a Mirror intent-check on every output, and an HMAC-sealed chain that cryptographically pins every refused-harm and neutralized-drift event to its predecessor. An in-process autonomy scanner runs the full pytest suite every six hours and posts a signed verdict at /api/autonomy/verdict — the system can answer, at any moment, whether it is operating correctly, without a human present.
Live system · real chain, real receipts, real events · open for the world to plug in, connect, and use
This is a self-funded project to create a global AI that anyone can help build. Every fact you anchor, every claim you verify, every contradiction you catch mints AEGIS tokens as proof you helped build the database — that's the thank-you and it always will be. If you support this and want to help keep the system on, any donation is welcome.
Donations do not unlock any tier and do not require a receipt. Everything the Sentinel does — anchoring facts, minting AEGIS, sealing the chain — stays free and open for anyone. This is a trust-based ask.