惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
Jina AI
Jina AI
博客园 - Franky
Apple Machine Learning Research
Apple Machine Learning Research
酷 壳 – CoolShell
酷 壳 – CoolShell
阮一峰的网络日志
阮一峰的网络日志
量子位
雷峰网
雷峰网
宝玉的分享
宝玉的分享
V
Visual Studio Blog
博客园_首页
小众软件
小众软件
The Cloudflare Blog
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
大猫的无限游戏
大猫的无限游戏
博客园 - 聂微东
S
SegmentFault 最新的问题
博客园 - 【当耐特】
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
博客园 - 叶小钗
月光博客
月光博客
博客园 - 三生石上(FineUI控件)
人人都是产品经理
人人都是产品经理
WordPress大学
WordPress大学

Hacker News: Show HN

PurrrrrFocus: Pomodoro Timer App - App Store Workflow Engine — Multi-Step Orchestration for Bun RapidPhoto: Pro Photo Editor App - App Store GitHub - DheerG/swarms: Achieve extraordinary results with claude code across a variety of tasks SPICE simulation → oscilloscope → verification with Claude Code — Lucas Gerads Show HN: VCoding – A 5 MB native Windows IDE with no dynamic dependencies Show HN: LLMs don't hallucinate because they're bad at math, it's the format GitHub - Agent-FM/agentfm-core: AgentFM is a peer-to-peer network that turns everyday computers into a decentralized AI supercomputer. AgentFM lets you run massive AI workloads directly across a global mesh of idle CPUs and GPUs. Show HN: Tracking Top US Science Olympiad Alumni over Last 25 Years GitHub - Potarix/agent-hub: One place to talk to all your agents Show HN: Runtime security for AI agents(injection,tool abuse, data exfiltration) GitHub - dubeyKartikay/lazyspotify: Terminal Spotify client for macOS and Linux GitHub - the-banana-tool/king-louie: Easy to use GUI Personal AI Assistant. Win/Linux/Mac. Show HN I made my vacation rental bookable by AI agents–no Airbnb, 0% commission GitHub - basteez/jsf-autoreload: maven plugin to enable hot reload on jsf projects uvm32/hosts/host-gdbstub at main · ringtailsoftware/uvm32 GitHub - labsai/EDDI: Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus. GitHub - glitchnsec/fortyone-oss: AI Executive Assistant Platform Quickstart | Alien GitHub - muxshed/shed: One stream in, or many. Every destination, simultaneously. No cloud middleman, no per-channel fees, no limits. GitHub - ocrbase-hq/ocrbase: 📄 PDF/IMG ->.MD/JSON Document OCR API for PaddleOCR and GLMOCR. Self-hostable. GitHub - impactjo/home-memory: MCP server that lets your AI assistant remember everything about your home. GitHub - Sets88/dbcls: DbCls is a powerful terminal database client that supports various databases GitHub - neptun2000/heor-agent-mcp GitHub - SeanFDZ/macmind: Single-layer transformer in HyperTalk for the classic Macintosh RollQuation: Math Puzzles - Apps on Google Play GitHub - dropbox/witchcraft Show HN: Agent-cache – Multi-tier LLM/tool/session caching for Valkey and Redis GitHub - opentalon/opentalon: OpenTalon is an open-source platform built from the ground up in Go as a robust alternative to OpenClaw LinkedIn™ 职位抓取工具 - Chrome 应用商店
GitHub - arian-gogani/nobulex: The accountability primiti...
arian_ · 2026-04-25 · via Hacker News: Show HN

CI OpenSSF Best Practices

AI agents can't prove they followed their own rules. Nobulex fixes that.

$ npx tsx examples/demo.ts

Agent A declares covenant: permit read, forbid transfer > 500
Agent A executes 5 actions...
  ✓ read /data/users — allowed
  ✓ transfer $300 — allowed
  ✓ read /data/orders — allowed
  ✗ transfer $600 — BLOCKED by covenant
  ✓ read /data/config — allowed

Agent B verifies Agent A...
  ✓ Step 1: Covenant signature valid
  ✓ Step 2: Proof signature valid
  ✓ Step 3: Log integrity verified (5 entries, chain intact)
  ✓ Step 4: Compliance check passed (0 violations)
  ✓ Step 5: History length sufficient (5 ≥ 1)
  ✓ Step 6: Covenant matches requirements
  ✓ Step 7: Audience binding confirmed
  ✓ Step 8: Task class verified

Result: Agent B trusts Agent A ✅

Agent C presents tampered proof...
  ✓ Step 1: Covenant signature valid
  ✓ Step 2: Proof signature valid
  ✗ Step 3: FAILED — hash chain broken at entry 2

Result: Agent B refuses Agent C ❌

Three primitives. That's the whole protocol:

  1. Declare — write rules: permit, forbid, require
  2. Enforce — check every action before it runs
  3. Prove — tamper-evident hash chain anyone can verify

Tests License TypeScript

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

What is Proof-of-Behavior?

You can't audit a neural network. But you can audit actions against stated commitments.

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

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

Proof-of-behavior means every autonomous agent action is:

  • Declared — behavioral rules defined before deployment in a formal language
  • Enforced — violations blocked at runtime, before execution
  • Proven — every action hash-chained into a tamper-evident audit trail that third parties can independently verify

Quick Start

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);   // []

Cross-Agent Verification Handshake

Before two agents transact, they verify each other's proof-of-behavior. No proof, no transaction.

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

// Agent A generates its proof-of-behavior
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.

Why Proof-of-Behavior Matters

What exists today What's missing
Guardrails filter prompts and outputs No proof the agent followed rules at the action layer
Monitoring watches what agents do after the fact No enforcement before execution
Identity verifies who the agent is No verification of what the agent did
Governance platforms provide dashboards and policies No cryptographic evidence a third party can independently verify

Proof-of-behavior fills the gap: declare → enforce → prove.

The Covenant DSL

covenant SafeTrader {
  permit read;
  permit transfer (amount <= 500);
  forbid transfer (amount > 500);
  forbid delete;
  require counterparty.compliance_score >= 0.8;
}

Forbid wins. If any forbid matches, the action is immediately blocked regardless of permits. Default deny for unmatched actions. Conditions support >, <, >=, <=, ==, != on numeric, string, and boolean fields.

Three keywords. No configuration files. No YAML. No JSON schemas. Just rules.

Architecture

┌─────────────────────────────────────────────────────────────┐
│                      Integrations                           │
│            mcp-server  ·  a2a  ·  langchain                 │
├─────────────────────────────────────────────────────────────┤
│                       User API                              │
│                         sdk                                 │
├─────────────────────────────────────────────────────────────┤
│                   Proof-of-Behavior                         │
│                                                             │
│  identity · covenant-lang · action-log · enforcement        │
│  middleware · verification · crypto · merkle · proofs       │
│                                                             │
│                         core                                │
└─────────────────────────────────────────────────────────────┘

Packages

Package What It Does
@nobulex/core Everything — identity (DIDs), covenant DSL, hash-chained action logs, enforcement middleware, verification, cryptographic proofs
@nobulex/sdk User-facing API — NobulexClient, CovenantAgent, cross-agent handshake
@nobulex/mcp-server MCP compliance server for Claude Desktop, Cursor, VS Code
@nobulex/a2a A2A Agent Card behavioral attestation extension
@nobulex/langchain LangChain callback integration
@nobulex/claude-agent-sdk Claude Agent SDK compliance hooks — PreToolUse/PostToolUse gating, tamper-evident tool-call logs

Integrations

  • npmnpm install @nobulex/sdk
  • MCPnpx @nobulex/mcp-server (works with Claude Desktop, Cursor, VS Code)
  • A2A — Agent Card behavioral attestation extension
  • LangChain — drop-in compliance callbacks

Conceptual Comparison

Bitcoin Ethereum Nobulex
What it verifies Monetary transfers Contract execution Agent behavior
Mechanism Proof of Work Proof of Stake Proof of Behavior
What's proven Transaction validity State transitions Behavioral compliance
Guarantee Trustless money Trustless contracts Trustless agents

Live Demo

npx tsx examples/demo.ts

Creates two agents, defines behavioral rules, enforces at runtime, blocks a forbidden transfer, generates a proof-of-behavior, runs the 8-step handshake, and then shows the same handshake rejecting a third agent whose log was tampered with — all in one script.

npx tsx examples/langchain-agent.ts   # covenant enforcement around a mocked LangChain agent
npx tsx benchmarks/bench.ts           # protocol performance on your hardware

Security Audit

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 — the handler never runs.

Known limitations:

  • No key revocation mechanism yet — compromised keys remain trusted until removed out-of-band.
  • No rate limiting on handshake verification — potential DoS vector under adversarial load.
  • Single-threaded chain verification — chains above ~100K entries take visible time (see benchmarks).
  • Clock skew tolerance is 0 — agents with desynchronized clocks may fail timestamp checks.

Not in scope:

  • Model-level safety (prompt injection, jailbreaking) — use guardrails for that.
  • Network transport security — use TLS.
  • Key storage — use your platform's HSM or key vault.

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

Development

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

Standards

Ecosystem

Projects building on or composing with Nobulex:

Partner Layer Integration
Dominion Observatory Pre-call trust scores Feeds trust_score into covenant require
SidClaw HITL approval Signed state-transition receipts
Aira Authorization + audit Multi-party signing with RFC 3161
Signet Signing layer Bilateral co-signing, policy attestation
AgentMint Runtime enforcement Ed25519 plan signing, scope matching
APS Receipt schema Co-designed outcome_hash format

Documentation

Links

License

MIT — use it for anything.