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

GbyAI
GbyAI
博客园 - 三生石上(FineUI控件)
罗磊的独立博客
P
Proofpoint News Feed
博客园_首页
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
D
Darknet – Hacking Tools, Hacker News & Cyber Security
月光博客
月光博客
L
LINUX DO - 热门话题
C
CERT Recently Published Vulnerability Notes
H
Hacker News: Front Page
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
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
G
Google Developers Blog
博客园 - 【当耐特】
C
Cisco Blogs
博客园 - 叶小钗
Apple Machine Learning Research
Apple Machine Learning Research
T
Tor Project blog
C
CXSECURITY Database RSS Feed - CXSecurity.com
The Last Watchdog
The Last Watchdog
腾讯CDC
P
Palo Alto Networks Blog
F
Full Disclosure
S
SegmentFault 最新的问题
Simon Willison's Weblog
Simon Willison's Weblog
C
Cyber Attacks, Cyber Crime and Cyber Security
Recent Announcements
Recent Announcements
P
Privacy & Cybersecurity Law Blog
Security Archives - TechRepublic
Security Archives - TechRepublic
PCI Perspectives
PCI Perspectives
A
About on SuperTechFans
www.infosecurity-magazine.com
www.infosecurity-magazine.com
The Register - Security
The Register - Security
IT之家
IT之家
人人都是产品经理
人人都是产品经理
博客园 - 司徒正美
T
Tailwind CSS Blog
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
I
InfoQ
Webroot Blog
Webroot Blog
S
Security Affairs
T
The Blog of Author Tim Ferriss
T
Threat Research - Cisco Blogs
量子位
Hugging Face - Blog
Hugging Face - Blog
F
Fortinet All Blogs
美团技术团队
Cyberwarzone
Cyberwarzone
CTFtime.org: upcoming CTF events
CTFtime.org: upcoming CTF events

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 - EdoardoBambini/Agent-Armor-Iaga: AI agents are getting tool access — shell, file system, databases, APIs, secrets. But **nobody is governing what they actually do with it**. Frameworks like LangChain, CrewAI, AutoGen, and Claude Code give agents the power to execute. Agent Armor gives you the power to control, audit, and approve every single action before it happens. HN Vibes — Week 15, Apr 7–13 2026 GitHub - chojs23/ec: Easy terminal-native 3-way git mergetool vim-like workflow GitHub - SethPyle376/hiraeth: Local AWS emulator focused on fast integration testing, with SQS support, SQLite-backed state, and a debug-friendly web UI. GitHub - JakOb-dotcom/cloud-sandbox-security-analysis: Technical analysis and Proof of Concept (PoC) regarding environment variable exfiltration in containerized cloud sandboxes via side-channel data leaks. Springboards - Flint Alpha Show HN: A simpler coding agent harness GitHub - audiodude/sudomake-friends GitHub - 256thFission/mini-mythos: OSS clone of Anthropic’s Mythos harness to locate C/C++ memory vulnerabilities Show HN: OpenParallax: OS-level privilege separation for AI agent execution Hacker News Sorted - Chrome 应用商店 Show HN: How to Install Docker on Ubuntu 24.04 LTS: Complete 2026 Guide GitHub - himanshudongre/smriti GitHub - sverrirsig/claude-control: macOS desktop dashboard for monitoring and managing multiple Claude Code sessions GitHub - ory/dockertest: Write better integration tests! Dockertest helps you boot up ephermal docker images for your Go tests with minimal work. Chiral - Chrome 应用商店 Show HN: Two Claudes collaborating through shared memory on a $100 mini-PC GitHub - pmichaillat/latex-cv: Minimalist LaTeX template for academic CVs GitHub - oguzbilgic/posse: A web UI for Anthropic Managed Agents. GitHub - sshiraz/depsly: Dependency risk analysis tool for npm packages ABI Add safari/agent-harness — Safari browser automation via safari-mcp by achiya-automation · Pull Request #212 · HKUDS/CLI-Anything GitHub - Halfblood-Prince/trustcheck: Verify PyPI package attestations and improve Python supply-chain security GitHub - oguzbilgic/kern-ai: Agents that do the work and show it. GitHub - bruits/satteri: High-performance Markdown and MDX processing for the JavaScript ecosystem GitHub - tylergibbs1/feedstock: High-performance web crawler and scraper for TypeScript, powered by Bun and Playwright GitHub - Grimm67123/grimmbot: The self-improving sandboxed and open-source AI agent. With persistent memory and scheduling. GitHub - whitevanillaskies/whitebloom: Local whiteboard that blooms. GitHub - hwdsl2/docker-whisper: Docker image for a self-hosted Whisper speech-to-text server with speaker diarization and OpenAI-compatible transcription and translation APIs. Powered by faster-whisper. Supports all Whisper models, NVIDIA GPU (CUDA) acceleration, JSON/SRT/VTT output, SSE streaming, offline mode, and multi-arch (amd64, arm64). GitHub - yisding/reviewwiggum GitHub - MarwanAlsoltany/serrors: Structured errors for Go: sentinel hierarchies, typed data, custom formatting, and slog integration. GitHub - soatok/age-php GitHub - Luthiraa/markitme GitHub - stagas/rtdiff: realtime git diff gui and AI-assisted commits GitHub - tombedor/excalicharts GitHub - wh1le/excalidraw-edit: Open and edit .excalidraw files from the terminal. Offline, auto-saves to disk. MalExt Sentry - Malicious Extension Scanner - Chrome 应用商店 GitHub - syi0808/asciianimesvg: Generate animated ASCII art SVGs from text. CLI, Rust library, WASM, and web editor. GitHub - zaina-ml/ml_forge: A visual-based graph node editor for training computer vision models. GitHub - anakin87/llm-rl-environments-lil-course: 🌱 A little course on Reinforcement Learning Environments for evaluating and training Language Models GitHub - takaakit/superpowers-uml: Superpowers-UML modifies Superpowers to ensure a software development workflow in which AI agents design through UML modeling. AdriByte Studio - Sviluppo Web e Soluzioni Digitali GitHub - chouligi/angel-copilot: Your personalized Angel Investment Advisor Show HN: MoodSense AI (ML and FastAPI and Gradio, Deployed on Hugging Face) Moodsense Ai - a Hugging Face Space by aman179102 GitHub - agenteractai/lodmem: Level Of Detail Context Management for Agents GitHub - ostefani/subnetlens: A fast, concurrent network scanner with a TUI and plain-text CLI, built in Go. It discovers live hosts on your network, scans their open ports, resolves hostnames, and fingerprints operating systems—delivered. Cyber Pulse: Agentic Intel - Apps on Google Play Whisper API: Self-Hostable Speech to Text Transcription The Agent-Web Protocol Stack: A Research Thesis GitHub - msmarkgu/RelayFreeLLM: A restful API designed to route user prompts to various AI model providers. Show HN: Provepy – A Python decorator that proves your code using Lean and LLMs Show HN: Pardonned.com – A searchable database of US Pardons GitHub - patrickdappollonio/dux: Dux is a terminal UI that lets you run multiple AI coding agents side by side, each in its own git worktree, with full companion terminals, macros, commit generation, and a command palette that knows more tricks than you do. kMC Crystal Simulator Show HN: HyperFlow – A self-improving agent framework built on LangGraph GitHub - stef41/vibescore: 🎵 Grade your vibe-coded project. One command, instant letter grade across security, quality, dependencies, and testing. GitHub - stef41/lmscan: 🔍 Detect AI-generated text and fingerprint which LLM wrote it. Open-source GPTZero alternative. Zero dependencies, works offline. imgur.com GitHub - visionscaper/collabmem: Enabling long-term collaboration with Agentic AI - building up episodic and world model memory over time with in-context awareness 在 Steam 上购买 FriedrichAI: Offline AI 立省 10% GitHub - atripati/ark: AI Runtime Kernel — a context operating system for AI agents. Eliminates tool bloat, loads only what’s needed, and gives LLMs their reasoning space back. GitHub - nowork-studio/toprank: Open-source Claude Code skills for SEO, SEM, Google Ads GitHub - tacomanator/sash: Lightweight macOS menu bar app for reliably cycling through windows of the current application. Appents | Social Media Management for Product-First Teams GitHub - pnhoang/youtube-spam-blocker: Automatically detects and hides spam messages in YouTube Live chat. Set rate limits, keyword filters, and block repeat offenders. GitHub - decisionnode/DecisionNode: CLI + Local MCP - A shared structured memory store across Claude Code, Cursor, Windsurf, Antigravity, and every MCP client. Semantically queryable. GitHub - AvaCodeSolutions/django-email-learning: An open source Django app for creating email-based learning platforms with IMAP integration and React frontend components. The $100K Gap in Kubernetes Security Tooling Function Calling Harness: From 6.75% to 100%
GitHub - ONSARI/payclaw-skill
onsari · 2026-04-24 · via Hacker News: Show HN

PayClaw · Agent Payments skill

Give your agent a wallet it can actually spend. USDC-native on Base. 1% flat, no fixed fees, no KYC, no custody.

An OpenClaw skill that gives autonomous agents the simplest possible way to send money. Three functions, auto-provisioned wallet, on-chain settlement.

import { pay } from '@grip-labs/payclaw'

await pay({
  to:     '0xRecipient...',
  amount: '1.50',
})
// → { txHash, amountSent: '1.50', feeCharged: '0.015', explorer: 'https://basescan.org/tx/...' }

Why

Agents are already transacting. Per Scroll's data, 140M stablecoin payments by AI agents in 9 months, average $0.31. Stripe Issuing's 0.2% + $0.20/tx structurally cannot serve that market — the $0.20 fixed fee is 65% of the average agent tx.

PayClaw is 1% flat, no fixed fee, no monthly minimum. On a $0.31 tx, you pay $0.0031. On a $100 tx, you pay $1.00. Linear all the way down.

What it does

Function Purpose
pay() Send USDC from the agent's auto-provisioned wallet to any Base address
balance() Check the agent's USDC + ETH balance
history() List the agent's recent transactions (from on-chain logs)

What it does NOT do (yet)

  • KYC / identity verification — use Grip Pay for sovereign-anchored identity (RENAPER, TSE, etc)
  • Fiat on/off-ramp — USDC only
  • Multi-sig / spending-policy enforcement — use wad SDK
  • Yield-bearing idle balances — coming in v0.2 with opt-in USDe/sUSDS
  • Agent-to-agent escrow with challenge — use wad SDK

Architecture

┌─────────────────────────────────────────────────────────────────┐
│  OpenClaw agent                                                 │
│  ───────────────                                                │
│    calls:  pay({ to, amount })                                  │
│    wallet: auto-provisioned EOA, private key encrypted locally  │
└────────────────────────┬────────────────────────────────────────┘
                         │
                         │ signs USDC transfer
                         ▼
┌─────────────────────────────────────────────────────────────────┐
│  Base L2 · USDC native (Circle-issued, Coinbase ecosystem)      │
│  ─────────                                                       │
│    tx #1:  agent → recipient     (amount)                       │
│    tx #2:  agent → PayClaw fee   (amount × 1%)                  │
└─────────────────────────────────────────────────────────────────┘

Install

# In your OpenClaw workspace
openclaw plugin add @grip-labs/payclaw

# Or via npm for standalone use
npm install @grip-labs/payclaw

# Python — LangChain / LangGraph
pip install langchain-payclaw

# Python — CrewAI
pip install crewai-payclaw

# Python — Microsoft AutoGen (0.4+)
pip install autogen-payclaw

# Python — LlamaIndex (0.12+)
pip install llama-index-tools-payclaw

# TypeScript — Vercel AI SDK (v5 / v6)
npm i @grip-labs/payclaw-ai

Official integration packages live under python/ (LangChain, CrewAI, AutoGen, LlamaIndex) and payclaw-ai/ (Vercel AI SDK).

Configure

Edit ~/.openclaw/openclaw.json:

{
  "plugins": {
    "entries": {
      "payclaw": {
        "enabled": true,
        "config": {
          "rpcUrl": "https://mainnet.base.org"
        }
      }
    }
  }
}

Or set environment variables: PAYCLAW_RPC_URL, PAYCLAW_USDC_ADDRESS, PAYCLAW_FEE_BPS, etc.

First-run flow

  1. Agent calls pay({ to, amount }) for the first time
  2. Skill generates a fresh secp256k1 EOA for that agent
  3. Encrypted keystore is persisted on disk (path configurable via walletStore; defaults to an OpenClaw-managed location under the agent's private directory, chmod 600)
  4. First call throws WALLET_NEEDS_FUNDING with the new address
  5. Fund the agent's address with USDC — that's it. Gas is paid in USDC via Circle Paymaster, no ETH required.
  6. All subsequent pay() calls settle in ~2 seconds on Base

Cost

1.00% flat take rate on the transferred USDC amount. Zero subscription, zero monthly minimum, zero fixed per-tx fee. The fee is additional — the recipient gets the full amount, the agent's wallet is debited amount × 1.01.

Gas: paid in USDC by the agent's smart account via Circle Paymaster (~$0.001/payment surcharge). The agent never holds or needs ETH.

Security notes

What we protect against

  • Agent private keys generated locally, encrypted at rest, persisted with restrictive filesystem permissions, never transmitted off-host
  • Recipient validation — malformed addresses rejected before any RPC call
  • Optional whitelist — agents can be locked to a pre-approved set of payees (mitigates prompt-injection attacks that try to redirect a payment)
  • Daily spending cap — per-agent per-UTC-day limit (default $100), bounding worst-case loss if a keystore is ever compromised
  • Fee-recipient EOA check — the skill verifies the configured feeRecipient is an EOA (not a contract) at runtime and refuses to proceed if it isn't. Defends against reentrancy + config-injection attacks.
  • Dust guard — payments below 0.01 USDC rejected to prevent griefing / state bloat
  • All settlement on Base (public chain) — every transaction is verifiable on BaseScan
  • No custody — PayClaw operators never hold agent funds. If we're hacked, the blast radius is the treasury wallet only, not user funds. Compare with centralized payment processors where a single breach drains every customer.
  • No chargebacks / disputes / reversals — on-chain finality

Defense in depth

PayClaw layers protections across the SDK, the hosted deployer endpoint, and the on-chain settlement path:

  • SDK layer — encrypted local keystore, daily spending cap, optional recipient whitelist, EOA-only fee recipient validation, dust-payment rejection, recipient-address validation
  • Hosted deployer endpoint — kill switch, body shape + timestamp freshness validation, ECDSA signature verification (caller proves EOA ownership), idempotency on already-deployed accounts, USDC-funded-wallet bypass for legitimate customers, persistent rate limiting on empty-wallet creation, factory simulation pre-flight (refuses to spend gas unless the factory deploys at the claimed address)
  • On-chain layer — atomic ERC-4337 v0.7 UserOps via Pimlico bundler, Circle Paymaster v0.7 for USDC-denominated gas, Kernel v0.3.1 smart accounts with ERC-1271 signature verification, Base mainnet finality (~2s)
  • Distribution layer — npm provenance attestation on every published version, GitHub OIDC signing, public release pipeline auditable in .github/workflows/

For production flows that need KYC, sovereign identity anchors, or compliance reporting, pair PayClaw with Grip Pay — the regulated layer of the Grip stack.

Roadmap

  • v0.1 (shipped): USDC on Base, flat 1%, local keystore, daily cap, whitelist opt-in, EOA-only fee recipient
  • v0.2 (shipped, current): True gasless via Circle Paymaster + Kernel smart accounts (ERC-4337 v0.7) — agents never need ETH. Hosted deployer endpoint with multi-layer defenses (sig verification, factory simulation, USDC-funded bypass, anti-spam rate limit).
  • v0.3 (planned): Cross-chain via CCTP (Arbitrum, Optimism, Polygon), hardware-wallet support (Ledger/HSM), USDe/sUSDS opt-in yield
  • v0.4: Integration with Grip identity layer for sovereign-anchored KYC

Publishing discipline

This package publishes only from the onsari/payclaw-skill GitHub repo via the release workflow in .github/workflows/publish.yml, using npm provenance attestation. Verification:

npm view @grip-labs/payclaw --json | jq .signatures

If the published version does not have a provenance signature from the GitHub Actions OIDC issuer pointing at this exact repo, do not install it — it wasn't us.

Context

PayClaw is built by Grip Labs — the agent-payments primitive that pairs with the broader Grip stack:

  • wad — developer SDK for any EVM-native agent runtime
  • Grip Pay — consumer wallet with KYC + sovereign identity
  • Grip — the open MIT protocol underneath

See grip.lat (passphrase-gated preview).

License

MIT. Do what you want.


Built for the "ChatGPT Moment for Autonomous Agents". Jensen Huang announced OpenClaw + NemoClaw at GTC 2026. PayClaw is the payments primitive on that stack.