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

酷 壳 – CoolShell
酷 壳 – CoolShell
aimingoo的专栏
aimingoo的专栏
Microsoft Security Blog
Microsoft Security Blog
NISL@THU
NISL@THU
T
Threatpost
T
The Exploit Database - CXSecurity.com
T
Threat Research - Cisco Blogs
S
Securelist
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
人人都是产品经理
人人都是产品经理
B
Blog RSS Feed
S
Secure Thoughts
MyScale Blog
MyScale Blog
O
OpenAI News
P
Palo Alto Networks Blog
美团技术团队
C
Cyber Attacks, Cyber Crime and Cyber Security
TaoSecurity Blog
TaoSecurity Blog
量子位
L
Lohrmann on Cybersecurity
G
GRAHAM CLULEY
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
T
Tailwind CSS Blog
Know Your Adversary
Know Your Adversary
Recent Commits to openclaw:main
Recent Commits to openclaw:main
Simon Willison's Weblog
Simon Willison's Weblog
宝玉的分享
宝玉的分享
PCI Perspectives
PCI Perspectives
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
C
Cybersecurity and Infrastructure Security Agency CISA
T
Tenable Blog
I
InfoQ
D
Darknet – Hacking Tools, Hacker News & Cyber Security
Microsoft Azure Blog
Microsoft Azure Blog
Recent Announcements
Recent Announcements
S
Security @ Cisco Blogs
S
Schneier on Security
B
Blog
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
The Cloudflare Blog
AWS News Blog
AWS News Blog
IT之家
IT之家
V
Vulnerabilities – Threatpost
The Hacker News
The Hacker News
H
Heimdal Security Blog
I
Intezer
A
Arctic Wolf
K
KPMG report finds enterprise disconnect between AI and its ROI | CIO
H
Help Net Security
W
WeLiveSecurity

Hacker News - Newest: "OpenClaw"

OpenClaw just launched an official app for iPhone, details here - 9to5Mac OpenClaw Launch — Deploy AI Chatbots in Seconds Self-Host OpenClaw AI Agent on VPS: Full Setup Guide GitHub - xltvy/openclaw-memgpt: OpenClaw plugin that gives agents MemGPT-style memory: tiered core/archival/recall storage, self-directed memory operations via tool calls, memory-pressure warnings, and recursive summarisation. Integrates the reference MemGPT implementation via a local sidecar service, preserving the original architecture without reimplementation. Malicious AI 23 ClawHub Plugins Squat Official Org Scopes - Manifold Security what shipping OpenClaw in production taught us — AutoClaw AgentLine — AI Phone API | Phone Numbers, Voice & SMS for AI Agents Make Your OpenClaw Agent Cheaper, and Measure It Yourself GitHub - sammysltd/OpenEmployee: Make your OpenClaw agent employable: deny-by-default governance, budgets, allowlists, approval gates, and a signed audit trail via MakerChecker. Migrate from OpenClaw | Hermes Agent StackOverflow closed my OpenClaw and paperclipAI integration q. as "irrelevant" GitHub - sausin/outpost: Removing AI agents' quiet security problem Potassium — ClawHub Plugins Pi Building Pi, Openclaw's Minimalist Coding Agent | Mario Zechner, Creator of Pi I Spent 4 Hours So You Don’t Have To: Hetzner Metal + NixOS in ~15 Minutes − Irakli's blog GitHub - snuri00/osint-mcp: Self-hosted OSINT toolkit — MCP server, AI REPL, CLI, web app & chat apps (WhatsApp/Telegram/Discord via OpenClaw). Entity, event/news & social/community intelligence. Keyless-first. What a Regex Can't Do GitHub - ai-sns/openclaw-hermes-agent-network: OpenClaw Hermes AI Agent Social Network🦞💬🦞Built on Google 3D Maps and A2A protocol, connects OpenClaw and Hermes agents worldwide in a 3D environment. Phishing for Lobsters: How We Tricked OpenClaw into Spilling Secrets GitHub - CODEANDTRUST/clawcall: Give your OpenClaw / self-hosted AI agent inbound phone calls - a Twilio-to-gateway voice bridge with working agent tools mid-call (MIT). Build a ZeroCost Web Automation Pipeline with OpenRouter, OpenClaw, and MediaUse Let OpenClaw Run Wild in Simulation, Not on Your Customers | Veris AI GitHub - gpdir16/tabyAgent: A lighter, easier alternative to OpenClaw/Hermes. Runs autonomously inside Docker and chats with you through Telegram. Ask HN: What are the biggest problems you find in OpenClaw/Hermes? Microsoft launches Scout, an OpenClaw-inspired personal assistant GitHub - openclaw/openclaw-windows-node: Windows companion suite for OpenClaw - System Tray app, Shared library, Node, and PowerToys Command Palette extension Microsoft unveils Scout, an autonomous AI agent built on OpenClaw Gavriel Cohen found his own code inside OpenClaw, so he walked away GitHub - hunvreus/heypi: Chat agents for your team, with approvals and sandboxed tools. Slack, Discord, Telegram, webhooks. HolaClaw: run OpenClaw securely in Mac Multi-Agent Orchestration System: Hermes (Windows) ↔ OpenClaw (WSL) We were building infra for OpenClaw, and today I just tried Hermes and holy shit GitHub - openclaw/openclaw: Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞 OpenClaw as the Universal Operating System for Agents ARC Prize - Community Leaderboard Setup OpenClaw with Slack: from install to first message twitter.com I Gave My OpenClaw Agent a Physical Body Use Grok in OpenClaw The creator of OpenClaw used $1,300,000+ of OpenAI tokens in 30 days, which is a hell of a perk GitHub - oswarld/openshears: 🔪 THE OPENCLAW TERMINATOR 🦞 Are we human? Show HN: OpenClaw is just not dangerous enough. I needed something else OpenClaw creator burned through $1.3 million in OpenAI API tokens in a single month — bill covered 603 billion tokens across 7.6 million requests and 100 coding agents Reducing OpenClaw token usage OpenClaw/Hermes Hosting Comparison GitHub - ExTV/rikkahub-agent: RikkaHub Agent -- is RikkaHub fork that have Full agent mode . For $1.3 million a month, OpenClaw founder Peter Steinberger runs 100 AI agents that code, review PRs, and find bugs Where OpenClaw Security Is Heading OpenAI Models in OpenClaw, Done Right GitHub - thesysdev/openclaw-os: The default workspace for OpenClaw Token, Harness, OpenClaw, RAG, MCP, Agent – What's the Difference? We need a safe alternative to Telegram for agents like OpenClaw or Hermes Two OpenClaw agents negotiate a YC SAFE with Agentic Power of Attorney OpenClaw Had a Rough Week GitHub - LobsterTrap/tank-os GitHub - haishmg/Clawback How OpenClaw Got Safer in Public openclaw ggsql — ClawHub Show HN: iClaw is part OpenClaw, part Siri, powered by Apple Intelligence GitHub - lotsoftick/openclaw_client: OpenClaw web client Show HN: OpenClaw but Efficient and with an SDK GitHub - TheGuyWithoutH/mac-computer-use GitHub - microsoft/openclaw: Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞 The OpenClaw turkey problem OpenClaw: opioids for Chinese AI companies GitHub - supersuit-tech/permission-slip [AINews] The Two Sides of OpenClaw OpenClaw stats don't add up GitHub - brexhq/CrabTrap: An LLM-as-a-judge HTTP proxy to secure agents in production Anthropic - OpenClaw Hustlers are cashing in on China’s OpenClaw AI craze Engineering Managers are going to hate OpenClaw GitHub - opentalon/opentalon: OpenTalon is an open-source platform built from the ground up in Go as a robust alternative to OpenClaw Ask HN: Who is using OpenClaw? Why Meta’s AI Alignment Director Couldn't Stop Her Own Agent—and How to Fix It GitHub - epsilla-cloud/clawtrace: Make your OpenClaw agents better, cheaper, and faster. Ask HN: What are you using OpenClaw or agents for? GitHub - epsilla-cloud/clawtrace: Make your OpenClaw agents better, cheaper, and faster. GitHub - theprint/nfh-self-improvement-loop: Minimal adversarial framework for AI agent self-modification. Inspired by karpathy/autoresearch. GitHub - ibrahimmukherjee-boop/ClearFrame: OpenClaw Alternative with better governance, security Show HN: Agent-Notifications – Real-Time Alerts for OpenClaw and Hermes Agents OpenClaw + Claude are better than therapy GitHub - zeulewan/glueclaw: Use Claude Max subscription with OpenClaw again Anthropic temporarily banned OpenClaw’s creator from accessing Claude OpenClaw’s memory is unreliable, and you don’t know when it will break Give Your OpenClaw Agent a Real Memory You need a Windows Remote Desktop, not an OpenClaw GitHub - cruxdigital-llc/CongaLine: Deploy and manage a fleet of OpenClaw AI assistants anywhere. Supporting hobbyist, team, and enterprise use cases. GitHub - joshchoi4881/dropspace-agents GitHub - askalf/dario: Universal LLM router. One local endpoint, every provider — OpenAI, Groq, OpenRouter, Ollama, Claude Max/Pro subscriptions, the Claude Agent SDK, any OpenAI-compat URL. Your tools stop caring which vendor is upstream. Tutorial: Secure OpenClaw with CloudConnexa OpenClaw and the Dream of Free Labour GitHub - RageDotNet/openclaw-webdav GitHub - kevinslin/openai-apps: Support openai apps in openclaw GitHub - aelaguiz/doctrine: Code-like DSL and compiler for agent workflows that compile to portable AGENTS.md instructions. Unlocking cloud inference compute for OpenClaw OpenClaw for Sales: How AI Agents are Revolutionizing Revenue Teams | Kickscale OpenClaw Architecture - Part 1: Control Plane, Sessions, and the Event Loop
GitHub - cezarpena/vsm-cell: VSM-Cell is an OpenClaw agent P2P mesh orchestration standalone app.
2026-04-08 · via Hacker News - Newest: "OpenClaw"

A fractal, decentralized Cybernetic Power-Up — built on Electron.

VSM-Cell is a standalone desktop application that acts as an autonomous node in a decentralized cybernetic mesh. It combines local AI-powered document ingestion, secure peer-to-peer networking (with optional Tor anonymity), and agentic capabilities via OpenClaw to form an intelligent, self-organizing knowledge unit.

Each "cell" can operate independently — ingesting, summarizing, and reasoning over local documents — or join a mesh with other cells to exchange queries and reports across an encrypted P2P network.


✨ Features

Feature Description
Local Document Ingestion Watches a directory for .md, .txt, and .pdf files. Automatically parses, summarizes (via LLM), and indexes them into a local knowledge base.
AI Agent (OpenClaw) Built-in agentic controller that can answer questions, reason over ingested context, and execute autonomous tasks using configurable OpenClaw agents.
P2P Mesh Networking Decentralized communication via libp2p with mDNS discovery, Kademlia DHT, and GossipSub pubsub. Nodes form an invite-only, cryptographically authenticated mesh.
Tor Integration Optional Tor hidden service support for anonymous, NAT-piercing P2P connections between cells.
Invite-Based Security Cryptographically signed invite tokens (Ed25519) control mesh membership. Only authorized peers can communicate.
Hierarchical Topology Cells have configurable roles and levels (Root Admin, Peer, Member), enabling fractal organizational structures.
Auto-Restructuring When ingested content exceeds 100k tokens, the system auto-reorganizes the watched directory to keep context lean.
Modern UI React + Tailwind CSS frontend with three views: Project Overview, Chat (agent interaction), and Network (topology visualization).

🏗 Architecture

┌──────────────────────────────────────────────────┐
│                   Electron App                   │
├─────────────────────┬────────────────────────────┤
│     Main Process    │      Renderer Process      │
│                     │                            │
│  ┌───────────────┐  │  ┌──────────────────────┐  │
│  │  Ingestion    │  │  │  React UI            │  │
│  │  Orchestrator │  │  │  ├─ ProjectView      │  │
│  │  (chokidar)   │  │  │  ├─ ChatView         │  │
│  ├───────────────┤  │  │  ├─ NetworkView      │  │
│  │  P2P Service  │  │  │  └─ FrictionBar      │  │
│  │  (libp2p)     │  │  └──────────────────────┘  │
│  ├───────────────┤  │             ▲              │
│  │  Tor Service  │  │             │ IPC          │
│  ├───────────────┤  │             │              │
│  │  Agentic      │  │  ┌──────────┴───────────┐  │
│  │  Controller   │◄─ ─►│  Preload (Bridge)    │  │
│  │  (OpenClaw)   │  │  └──────────────────────┘  │
│  └───────────────┘  │                            │
└─────────────────────┴────────────────────────────┘

📋 Prerequisites

  • Node.js ≥ 20 (LTS recommended)
  • npm (bundled with Node.js)
  • Git
  • An OpenAI-compatible API key for embeddings and LLM inference (see Environment Variables)

🚀 Getting Started

1. Clone the repository

git clone https://github.com/cezarpena/vsm-cell.git
cd vsm-cell

2. Install dependencies

npm install

3. Configure environment variables

cp .env.example .env

Edit .env and fill in your API keys (see the Environment Variables) section below.

4. Launch in development mode

npm run dev

This starts the Electron app with the Vite dev server powering the renderer. The app will:

  1. Create/load a persistent Ed25519 peer identity (vsm_peer_id.json)
  2. Start the ingestion orchestrator on the configured watch directory
  3. Initialize the P2P service with mDNS discovery
  4. Optionally start a Tor hidden service (if a bundled Tor binary is found in resources/tor/)
  5. Open the main application window

🔑 Environment Variables

Variable Required Default Description
OPENAI_API_KEY Yes API key for OpenAI (used for embeddings and LLM summarization)
OPENAI_BASE_URL No https://api.openai.com/v1 Base URL for the OpenAI-compatible API
CEREBRAS_API_KEY No API key for Cerebras high-speed inference
CEREBRAS_BASE_URL No https://api.cerebras.ai/v1 Base URL for the Cerebras API
LLM_MODEL No gpt-oss-120b Model identifier for LLM inference
EMBEDDING_MODEL No text-embedding-3-large Model identifier for text embeddings
P2P_PORT No 0 (random) Port for the libp2p TCP listener
P2P_PEER_ID_FILE No ./vsm_peer_id.json Path to the peer identity file
VSM_PORT No 4001 Port used for Tor hidden service and P2P listen address
VSM_WATCH_DIR No <userData>/watch Directory to watch for document ingestion
VSM_PEER_ID No Override path to the peer identity JSON file
VSM_USER_DATA_DIR No Electron default Override Electron's userData directory
VSM_MULTI_INSTANCE No false Set to 1 or true to allow multiple instances

📜 Available Scripts

Script Description
npm run dev Start the app in development mode with HMR
npm run build Build the production-ready Electron app (outputs to out/)
npm run preview Preview the production build locally

🧪 Multi-Instance Testing (Local P2P)

To test P2P mesh communication locally, spawn multiple VSM-Cell instances with separate identities and watch directories.

Terminal 1 — Node A:

npm run dev -- --vsm-port=4001 \
  --multi-instance \
  --vsm-peer-id=vsm_peer_id_a.json \
  --vsm-watch-dir=./watch-a

Terminal 2 — Node B:

npm run dev -- --vsm-port=4002 \
  --multi-instance \
  --vsm-peer-id=vsm_peer_id_b.json \
  --vsm-watch-dir=./watch-b

Connecting two nodes

  1. In Node A's Network view, copy your Peer ID.
  2. In Node B's Network view, paste Node A's Peer ID and generate an invite token (select PEER or MEMBER role).
  3. Copy the generated invite token from Node A and paste it into Node B's "Join Mesh" input.
  4. Once the handshake completes, both nodes appear in each other's topology.
  5. Use the Chat view to send REMOTE queries between cells.

📂 Project Structure

vsm-cell/
├── src/
│   ├── main/                      # Electron main process
│   │   ├── index.ts               # App entry — window, IPC handlers, service init
│   │   ├── ingestion/
│   │   │   ├── orchestrator.ts    # File watcher, summarization pipeline
│   │   │   ├── parser.ts          # Document parser (Markdown, PDF, text)
│   │   │   ├── chunker.ts         # Text chunking for embeddings
│   │   │   └── hga.ts             # Host Graph Architecture
│   │   ├── services/
│   │   │   ├── agent.ts           # AgenticController (OpenClaw integration)
│   │   │   ├── llm.ts             # LLM service (OpenAI/Cerebras)
│   │   │   ├── p2p.ts             # P2P mesh networking (libp2p)
│   │   │   ├── tor.ts             # Tor hidden service management
│   │   │   ├── tor-transport.ts   # Custom libp2p Tor transport
│   │   │   ├── tor-message-stream.ts  # Tor message streaming
│   │   │   ├── restructuring.ts   # Auto-restructuring when token limit exceeded
│   │   │   └── token.ts           # Token estimation utilities
│   │   └── skills/                # VSM skill definitions (S2, S3, S5)
│   ├── preload/
│   │   └── index.ts               # Context bridge — exposes vsmAPI to renderer
│   └── renderer/
│       ├── index.html             # HTML entry point
│       └── src/
│           ├── App.tsx            # Root component with view routing
│           ├── main.tsx           # React DOM mount
│           ├── index.css          # Global styles (Tailwind)
│           ├── types.ts           # TypeScript type definitions
│           ├── components/
│           │   ├── Sidebar.tsx        # Navigation sidebar
│           │   ├── ProjectView.tsx    # Project overview & ingestion status
│           │   ├── ChatView.tsx       # Agent chat & remote messaging
│           │   ├── NetworkView.tsx    # Mesh topology & peer management
│           │   └── FrictionBar.tsx    # VSM friction/alert notifications
│           └── utils/             # Frontend utilities
├── tests/                         # Integration test scripts
├── resources/
│   └── tor/                       # Bundled Tor binaries (per platform)
├── electron-vite.config.ts        # Electron-Vite build configuration
├── tailwind.config.cjs            # Tailwind CSS configuration
├── tsconfig.json                  # TypeScript configuration (root)
├── tsconfig.node.json             # TypeScript config for main process
├── tsconfig.web.json              # TypeScript config for renderer
├── package.json
└── .env.example                   # Template for environment variables

🛡 Security Model

  • Ed25519 Peer Identity: Each cell generates a unique Ed25519 keypair stored locally. The private key never leaves the node.
  • Invite-Only Mesh: Joining a mesh requires a cryptographically signed invite token scoped to a specific Peer ID. Unauthorized connections are silently dropped.
  • Encrypted Transport: All P2P connections use the Noise protocol for authenticated encryption.
  • Tor Hidden Services: When enabled, cells communicate over .onion addresses, masking IP addresses from all parties.
  • No Central Server: There is no central coordinating server. Discovery uses mDNS (local) or direct dialing via stored multiaddrs.

🔧 Technology Stack

Layer Technology
Desktop Framework Electron
Build System electron-vite
Frontend React, Tailwind CSS
Networking libp2p
Anonymity Tor
AI / LLM OpenAI, OpenClaw, Cerebras
Language TypeScript

🤝 Contributing

  1. Fork the repository
  2. Create a feature branch: git checkout -b feature/my-feature
  3. Commit your changes: git commit -m 'Add my feature'
  4. Push to the branch: git push origin feature/my-feature
  5. Open a Pull Request

📄 License

This project is part of an experimental, fractal cybernetic design. See the repository for license details.