[nobulexdev]

I am 15 (sophomore in high school). I have been building Nobulex for the past several months, including 60 npm packages, 134K lines of TypeScript and 6,115 tests.

The problem: AI agents are making real decisions for loans, trades, hiring, diagnostics with zero cryptographic proof of what they have done or whether they followed any rules. The EU AI Act requires tamper-evident audit trails by August 2026. Nobody has infrastructure for this.

Nobulex is three things:

Agents will be able to sign behavioral covenants before they act (cryptographic commitments — "I will not do X")

Middleware enforces those covenants at runtime as violations are blocked before execution

Every action is logged in a hash-chained, merkle-tree audit trail that anyone can use and verify independently

The quickstart is 3 lines: const { protect } = require('@nobulex/sdk'); const agent = await protect({ name: 'my-agent', rules: ['no-data-leak', 'read-only'] });

npm install @nobulex/sdk

Everything is MIT licensed and on npm under @nobulex/*. Site: https://nobulex.com

Would love feedback on the architecture, the covenant model, or anything else. Happy to answer questions.

[mlyle]

It looks almost entirely envisioned and implemented by AI.

An agent signing a covenant doesn't do anything. You're not going to enforce a contract against it, and there's not some kind of non-repudiation problem to solve.

Enforcing behavioral covenants or boundaries is inherent to how you make things safe. But how do you really do it for anything that matters? How do you make sure that an agent isn't discriminating based on race or other factors?

The whole reason you're using an LLM is because you're doing something either:

A) at very low scale, at which case it's hard to capture sufficient covenants cost-efficiently

or B) with very great complexity, where the behavior you want is hard to encapsulate in code-- in which case meaningful enforcement of the complex covenants that may result is hard.

Indeed, if you could just write code to do it, you'd just write code to do it.

I'm glad you're interested in these issues and playing with them. I'll leave you with one last thought: 134 KSLOC is a bug, not a feature. Some software systems that need to be huge, but for software systems that need to be trusted-- small, auditable, and understandable to humans (and agents) is the key thing you're looking for. Could you build some kind of small trustable core that solves a simple problem in an understandable way?

[nobulexdev]

You're right with the 134K point. The actual cryptographic kernel (covenant building, verification, hash-chaining) is just about 3-4K lines. The rest are just adapters, plugins and test harnesses. I should lead with that number. With enforcement, the covenant itself isn't the enforcement. Middleware intercepts tool calls before the execution and blocks the violations. But you're right that this only works for constraints you can express as rules. "No external calls" and "rate limit 100/hour" are enforceable. "Don't discriminate" is not — that's a fundamentally harder problem and I'm not pretending that it solves it. The small trustable core advice is truly good and probably what I should focus on next. Thank you.

[mlyle]

Why does whether the agent "commits" to a rule cryptographically matter?

Surely it's just the enforcement, and maybe the measuring of sentinel events -- how far does it wander off course.

How is cryptography an important part of this, given that we're talking about a layer that sits on top of an LLM without an adversary in-between?

I know you mention non-repudiation, but ... there's no kind of real non-repudiation here in this environment.

[nobulexdev]

Very fair question. If you control the whole stack with your agent, your middleware and your logs, then cryptography doesn't add much. You already trust yourself.

But, it matters when there are multiple parties. An enterprise deploys an agent that can handle customer data. The customer wants proof the agent has followed the rules. The regulator wants proof that the logs were not just edited after an incident. Without cryptographic signatures and hash chains, the enterprise can just say "trust us." With them, the proof is independently verifiable.

It's just the difference between "we followed the rules" and "here's a mathematically verifiable proof we followed the rules." For internal use, it's an overkill. For anything with external accountability, that targets the point.

[mlyle]

There's no mathematically verifiable proof that anyone followed the rules. There's a cryptographic chain, but it just means "this piece of the stack, at some point, was convinced to process this and recorded that it did this." -- not whether that actually happened, what code was running, etc.

It doesn't tell you anything about what code was running there or whether it was really enforced.

Look, it's cool that this is an area that interests you. But I want you to know that AI agents are sycophantic and will claim your ideas are good and will not necessarily steer you in good directions. I have patents in the area of non-repudiation dating back 25 years and am doing my best to give you good feedback.

Non-repudiation, policy enforcement, audit-readiness, ledgers: these are all good things. As far as I can tell, there's nothing too special about doing this with LLMs, too. The same kinds of code that a bank uses to ensure that its ledger isn't tampered with and that the right software is running in the right places would work for this job -- and it wasn't vibe coded and mostly specified by AI.

[nobulexdev]

You’re correct. The cryptographic chain proves “this middleware has processed this action and has recorded it,” not that the enforcement logic itself was correct or that the code running was what you think it was. Those are both different guarantees and I have been conflating them.

On “nothing too special about doing this with LLMs,” also fair. The primitives (policy enforcement, audit trails, non-repudiation) aren’t new. The bet is that AI agents will need these at a scale and standardization level that does not exist yet, and having it as a composable library matters when every framework (LangChain, CrewAI, Vercel AI SDK) is building agents differently. But the underlying cryptography isn’t novel.