Lab
Experiments in what AI can do, how to test it, and where human judgment belongs. Start with Sentinel’s public code and local demo, then explore the work still taking shape.
Featured · Open source
Does the action match the authorization?
An open-source testnet lab for checking an agent’s proposed blockchain transaction against a human-signed mandate. It connects the evaluation to execution of one exact call.
Testnet lab; no production security guarantee.
A transaction can call an allowed contract and stay under a spending limit while sending the purchase to the wrong person. Sentinel gives that failure a reproducible test: does this proposed action conform to what the owner signed?
The proposer has no signing authority. An evaluator checks the call’s decoded arguments and simulated effects against the mandate. A signer in a separate process attests the decision, and an execution contract checks that the submitted call matches the signed record.
You can follow that sequence through the source code, run the failure cases, and verify signed decision records. The repository includes the tests, adversarial findings and corrections behind its claims, so you can examine both the mechanism and the evidence for it.
Human authorization. Exact calls. Inspectable evidence.
Also on the bench
Tiny LLM Lab and Project Euclid remain in design and early build. Their public demos are still to come.
What lives here
Sentinel is available to explore now. More project code and write-ups will be linked here as they are released.
