Credit scores for AI agents. Autonomy earned, not granted.

AI agents get full access on day one and build zero track record. Nobulex fixes that.

Every agent starts restricted. As it performs reliably, it earns Trust Capital that unlocks higher autonomy, bigger transaction limits, lower insurance premiums, and enterprise approval. Agents that deviate lose access before the damage spreads. The same way credit scores turned lending into a scalable economic system, Trust Capital turns agent governance into one where reputation has real economic value.

If this is useful, star the repo to help others find it.

• Microsoft merged the core primitive into their Agent Governance Toolkit (PRs #1302, #1333)
• OpenLineage (Linux Foundation) accepted Nobulex into their ecosystem
• AAIF (Linux Foundation, founded by Anthropic/OpenAI/Google/Microsoft/AWS/Block) has the project under staff review
• State of Agent Security 2026 litepaper lists @nobulex/crypto as 10/10 conformance validated

npm install @nobulex/core
npx tsx examples/trust-capital-demo.ts

Agent starts at RESTRICTED tier (Trust Capital: 0)

Action 1: read_data — ALLOWED ✓ (Trust Capital: 12)
Action 2: read_data — ALLOWED ✓ (Trust Capital: 24)
Action 3: process_payment — BLOCKED ✗ (insufficient trust for financial ops)
Action 4: read_data — ALLOWED ✓ (Trust Capital: 36)
Action 5: read_data — ALLOWED ✓ (Trust Capital: 48)

Agent promoted to STANDARD tier
Action 6: process_payment — ALLOWED ✓ (Trust Capital: 65)
Action 7: approve_contract — BLOCKED ✗ (requires TRUSTED tier)

Agent promoted to TRUSTED tier (Trust Capital: 89)
Action 8: approve_contract — ALLOWED ✓

Try it live · Policy Designer · Quickstart · Compare · Receipt Schema · Pricing · IETF Draft

You can't audit a neural network. But you can audit actions against stated commitments — and accumulate that audit history into a reputation that has real economic value.

verify(covenant, actionLog) → { compliant: boolean, violations: Violation[], trustCapital: number }

This is always decidable, always deterministic, always efficient. No ML, no heuristics — mathematical proof.

Trust Capital means every autonomous agent action is:

• Declared — behavioral rules defined before deployment in a formal covenant
• Enforced — violations blocked at runtime, before execution
• Proven — every action hash-chained into a tamper-evident audit trail that third parties can independently verify
• Accumulated — verified behavior builds Trust Capital that gates future autonomy, transaction limits, insurance eligibility, and enterprise approval

npm install @nobulex/sdk

import { createDID, parseSource, EnforcementMiddleware, verify } from '@nobulex/core';

// 1. Create an agent identity
const agent = await createDID();

// 2. Write behavioral rules
const spec = parseSource(`
  covenant SafeTrader {
    permit read;
    permit transfer (amount <= 500);
    forbid transfer (amount > 500);
    forbid delete;
  }
`);

// 3. Enforce at runtime
const mw = new EnforcementMiddleware({ agentDid: agent.did, spec });

// $300 transfer — allowed
await mw.execute(
  { action: 'transfer', params: { amount: 300 } },
  async () => ({ success: true }),
);

// $600 transfer — BLOCKED before execution
await mw.execute(
  { action: 'transfer', params: { amount: 600 } },
  async () => ({ success: true }),  // never runs
);

// 4. Prove compliance
const result = verify(spec, mw.getLog());
console.log(result.compliant);    // true
console.log(result.violations);   // []

Before two agents transact, they verify each other's Trust Capital. No proof, no transaction.

import { generateProof, verifyCounterparty } from '@nobulex/sdk';

// Agent A generates its Trust Capital proof
const proof = await generateProof({
  identity: agentA,
  covenant: spec,
  actionLog: middleware.getLog(),
});

// Agent B verifies Agent A before transacting
const result = await verifyCounterparty(proof);

if (!result.trusted) {
  console.log('Refusing transaction:', result.reason);
  return; // No proof, no transaction
}

// Safe to transact — Agent A is verified
await executeTransaction(proof.agentDid, amount);

The handshake checks eight things in order: covenant signature, proof signature, log integrity, compliance, minimum history, required covenant, audience binding, and task class scoping. If any check fails, the transaction is refused.

Trust Capital fills the gap: declare → enforce → prove → accumulate.

npx tsx examples/demo.ts

Creates two agents, defines behavioral rules, enforces at runtime, blocks a forbidden transfer, generates Trust Capital proof, runs the 8-step handshake, and then shows the same handshake rejecting a third agent whose log was tampered with.

npx tsx examples/langchain-agent.ts   # covenant enforcement around a mocked LangChain agent
npx tsx examples/trust-capital-demo.ts # watch an agent earn credit through verified behavior
npx tsx benchmarks/bench.ts           # protocol performance on your hardware

We've conducted an internal security review. Here's what we tested and what we found:

Verified secure:

• Hash chain integrity: modifying any entry breaks the chain (property-tested with fast-check across random chains of varying length).
• Signature forgery: invalid signatures are rejected 100% of the time.
• Replay attack prevention: audience-bound proofs fail when replayed to a different verifier (property-tested).
• Covenant enforcement: forbidden actions are blocked before execution, never after.

Known limitations:

• No key revocation mechanism yet.
• No rate limiting on handshake verification.
• Single-threaded chain verification.
• Clock skew tolerance is 0.

See docs/threat-model.md for the full threat model.

git clone https://github.com/arian-gogani/nobulex.git
cd nobulex
npm install
npx vitest run             # full test suite (incl. fast-check property tests)
npx tsx examples/demo.ts   # see the protocol run end-to-end
npx tsx benchmarks/bench.ts

• IETF Internet-Draft — draft-gogani-nobulex-proof-of-behavior-00: Trust Capital Protocol for Autonomous AI Agents
• LangChain RFC #35691 — ComplianceCallbackHandler, 10+ implementations converging
• NIST RFI Response — Formal comments to NIST AI Agent Standards Initiative
• Microsoft AGT — Bilateral receipt primitive merged (PRs #1302, #1333)

Projects building on or composing with Nobulex:

• API Reference — Full API docs generated with TypeDoc (npm run docs:api)
• Trust Capital Spec — Formal standard specification (CC-BY-4.0)
• White Paper — Formal protocol specification
• Receipt Schema — Every field, verification steps, examples
• Getting Started — Developer guide

• Website: nobulex.com
• Try it: nobulex.com/try
• npm: @nobulex
• IETF: draft-gogani-nobulex-proof-of-behavior-00

MIT