Popular repositories Loading
-
receipt-desk
receipt-desk PublicA status desk that won't take an AI agent's word for "done": done, failed, or not shown, with the exact line it copied from the record.
HTML 1
-
sonny-test
sonny-test PublicThe Sonny Test: a check counts only if its verdict comes from a record the AI can't change, and it has already caught a fault planted on purpose. With its sealed record.
-
swarm-receipts
swarm-receipts PublicA planted-fault test bench for swarm oversight tools, and the sealed audit in which it caught two baseline checkers (AI Swarm Dynamics Hackathon, Oct 2026)
Python 1
-
receipt-pair
receipt-pair PublicTwo small AI models, run on your own PC by AMD's Lemonade, check whether an AI agent's "done" is true against its own log.
Python
-
-
iswt-research-record
iswt-research-record PublicSealed studies on whether an AI agent's 'done' can be trusted: designs, raw calls, scorers, receipts (3 to 7 Oct 2026)
Python
If the problem persists, check the GitHub status page or contact support.
