Skip to content

arian-gogani/nobulex

v1.0.0 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

accountability agent-governance ai-agents ai-security autonomous-agents compliance
+9 more
credit-score cryptography ed25519 eu-ai-act machine-trust mcp-server reputation trust-capital typescript

Affected surfaces

crypto_tls auth

Summary

AI summary

Cryptographic proof-of-behavior for AI agents with a Cedar-inspired DSL, hash‑chained logs, and DID identities across Core, Packages, and Stats.

Full changelog

What's in v1.0.0

Cryptographic proof-of-behavior for AI agents. Define behavioral constraints, enforce at runtime, prove compliance with hash-chained audit logs.

Core

  • Cedar-inspired constraint DSL (permit/forbid/require)
  • SHA-256 hash-chained action logs (tamper-evident)
  • Cross-agent verification handshake
  • DID-based agent identity
  • Merkle proof generation

Packages

  • @nobulex/core — constraint engine + enforcement
  • @nobulex/sdk — high-level CovenantAgent API
  • @nobulex/mcp-server — MCP compliance server
  • @nobulex/a2a — A2A Agent Card behavioral evidence extension
  • 26 packages total

Stats

  • 3,648 tests passing, 82 test files
  • TypeScript, MIT licensed
  • Registered issuer in Open Agent Trust Registry

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track arian-gogani/nobulex

Get notified when new releases ship.

Sign up free

About arian-gogani/nobulex

Proof-of-behavior enforcement for AI agents. Define behavioral covenant rules (permit/forbid/require), enforce at runtime before execution, get SHA-256 hash-chained tamper-evident audit logs, and verify compliance independently. Cross-agent verification handshake — no proof, no transaction. MIT licensed, 4,244 tests.

All releases →

Related context

Beta — feedback welcome: [email protected]