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

B
Blog RSS Feed
Spread Privacy
Spread Privacy
T
Threatpost
C
Cisco Blogs
P
Palo Alto Networks Blog
AI
AI
Cyberwarzone
Cyberwarzone
NISL@THU
NISL@THU
P
Privacy & Cybersecurity Law Blog
G
GRAHAM CLULEY
Simon Willison's Weblog
Simon Willison's Weblog
T
Tor Project blog
Latest news
Latest news
AWS News Blog
AWS News Blog
D
Docker
S
SegmentFault 最新的问题
博客园 - 聂微东
WordPress大学
WordPress大学
Vercel News
Vercel News
S
Securelist
爱范儿
爱范儿
J
Java Code Geeks
Know Your Adversary
Know Your Adversary
S
Schneier on Security
Hugging Face - Blog
Hugging Face - Blog
F
Fortinet All Blogs
Last Week in AI
Last Week in AI
D
DataBreaches.Net
宝玉的分享
宝玉的分享
D
Darknet – Hacking Tools, Hacker News & Cyber Security
MongoDB | Blog
MongoDB | Blog
Engineering at Meta
Engineering at Meta
K
Kaspersky official blog
美团技术团队
博客园 - 叶小钗
阮一峰的网络日志
阮一峰的网络日志
量子位
博客园_首页
Attack and Defense Labs
Attack and Defense Labs
S
Secure Thoughts
Google Online Security Blog
Google Online Security Blog
Application and Cybersecurity Blog
Application and Cybersecurity Blog
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
腾讯CDC
T
Threat Research - Cisco Blogs
雷峰网
雷峰网
有赞技术团队
有赞技术团队
www.infosecurity-magazine.com
www.infosecurity-magazine.com
P
Privacy International News Feed
S
Security Affairs

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 - devmegablaster/Notch-Pilot: A live companion for Claude Code that lives in your MacBook notch. Reacts to what Claude is doing, intercepts permission prompts, and shows all your running sessions at a glance.
devmegablast · 2026-04-17 · via Hacker News: Show HN

Notch Pilot

Your MacBook notch, but it's a live Claude Code dashboard.
Live usage limits, session status, permission prompts, and an animated buddy — all in the hole you already stare at.

Release License Platform Stars

Notch Pilot in action

Prefer higher quality? Watch the 720p MP4.


Install

brew tap devmegablaster/devmegablaster
brew install --cask notch-pilot

First launch: right-click Notch Pilot.app in /ApplicationsOpen (the app is ad-hoc signed, so Gatekeeper needs a one-time nod).

That's it. No menu bar icon. No dock icon. Hover the notch and the app reveals itself.

Prefer the direct long form: brew install --cask devmegablaster/devmegablaster/notch-pilot


What it actually does

Live Claude usage, right in the notch

The center of the expanded panel shows your real 5-hour session utilization % — the same number Claude's billing page shows you, not an estimate. Click it for the full breakdown: weekly limits (all models / Sonnet / Opus), extra-credit usage, reset countdowns, and today's input/output/cache token breakdown.

This works because Notch Pilot reads the Claude Code OAuth token the same way Claude Code itself does (via the security CLI) and hits Anthropic's oauth/usage endpoint directly. Nothing ships off your machine.

Live usage pill in the notch

A buddy that reacts to what Claude is doing

The collapsed pill carries one of six animated buddies — eyes, orb, waves, ghost, cat, bunny — in one of six colors. Each has seven expressions that fire based on what Claude is actually doing:

  • Focused (narrow, steady) — editing files
  • Active (pulsing) — running a tool
  • Curious (darting eyes) — permission request pending
  • Shocked (wide-eyed red) — dangerous command detected (rm -rf /, DROP TABLE, sudo rm, fork bombs, etc.)
  • Content (happy blinks) — 10-second farewell after activity ends
  • Idle / Sleeping — nothing happening

Permission prompts without leaving your editor

When Claude asks for permission to run a command, the notch expands into a structured view of the request. Shell commands get a code block. File edits get a red/green diff. URLs get a parsed host/path split. You get Deny, Allow, and Always allow <Tool> — the "always allow" path writes to ~/.claude/settings.json so Claude Code honors it natively next time.

AskUserQuestion gets the same treatment: each option becomes a clickable button.

Permission prompt rendered inside the notch

See every session at a glance

Hover the notch to see every live Claude session: project name, model, uptime, permission mode. Click a session to see its recent activity — user prompts, tool calls, assistant replies, errors — as a timeline. Click the arrow to jump to the hosting terminal; tmux pane navigation is supported, so it selects the exact pane running Claude before activating Alacritty, Terminal, iTerm, Ghostty, Kitty, WezTerm, Warp, and friends.

Session list in the expanded panel

Activity heatmap with history

A 24-hour activity strip per day, with arrows to walk back through previous days. Hover any cell to see which projects were active in that hour. Useful for noticing when you actually did the work vs when you think you did.

24-hour activity heatmap

Session finished? The buddy lets you know

When a Claude session wraps, the notch pops out of its hole into a bigger pill with the buddy centered and the project name below — so you can glance up from your editor and see that notch-pilot done without tabbing. Configurable and rate-limited; never interrupts.


Other things worth mentioning

  • Auto-start at login — registered via SMAppService, toggle in Behavior settings
  • Always-visible mode — pin the buddy to the notch even when nothing's running (idle peeks + zzz… text, default on)
  • Haptic feedback — a subtle .levelChange tick when the panel opens or closes (Force Touch trackpads only)
  • Voice announcements — optional per-event (permission / danger / session started / session finished), off by default
  • No menu bar, no dock icon — the notch is the entire surface. Quit lives on a power button in the expanded panel header.

Requirements

  • macOS 14 (Sonoma) or later with a MacBook notch (works on non-notched displays too, just less visually interesting)
  • Claude Code CLI signed in
  • Node.js on your PATH — the permission hook is a ~100-line Node script. Without it, sessions still show but permission interception won't work.

How it works

Notch Pilot watches three things:

  1. ~/.claude/projects/**/*.jsonl — Claude Code writes session transcripts here. The app tails the latest file every second, parses the last entry's tool_use block, and cross-references with live claude processes via libproc to filter dead sessions.
  2. A Claude Code hook auto-installed on first launch in ~/.claude/settings.json. On PermissionRequest / PreToolUse / UserPromptSubmit it pipes the event over a Unix domain socket (~/.notch-pilot/pilot.sock) to the running app. Permission prompts block the hook until the user clicks allow or deny.
  3. Anthropic's oauth/usage endpoint for the live usage percentages. Reads the Claude Code OAuth token via /usr/bin/security find-generic-password — the security CLI is on the Keychain credential's ACL allow-list, so reads succeed silently without password prompts.

The UI is an NSPanel hosting SwiftUI via NSHostingView, morphing between a collapsed pill and a full panel. The window resizes to fit content so clicks outside the pill pass through to whatever's underneath.


Privacy

Everything runs locally. No analytics, no telemetry, no network calls other than Anthropic's own usage endpoint (which Claude Code already uses on your behalf). The app only touches:

  • ~/.claude/projects/ (read — session transcripts)
  • ~/.claude/settings.json (read/write — installs the permission hook)
  • ~/.notch-pilot/ (read/write — hook script + Unix socket)
  • macOS Keychain item Claude Code-credentials (read — via the security CLI, the same way Claude Code uses it)

No account, no sign-up, no server-side anything.


Uninstall

brew uninstall --cask notch-pilot
rm -rf ~/.notch-pilot

Then open ~/.claude/settings.json and delete any hooks entries that reference ~/.notch-pilot/hook.js.


Build from source

Requires macOS 14+ and Swift 5.9+ (ships with Xcode Command Line Tools).

git clone https://github.com/devmegablaster/Notch-Pilot.git
cd Notch-Pilot
./scripts/build.sh         # produces dist/Notch Pilot.app
./scripts/make-dmg.sh      # produces dist/NotchPilot-<version>.dmg

No external dependencies. Everything's the standard library + Apple frameworks.


Contributing

PRs welcome — especially new buddy styles, colors, and platform integrations. See CONTRIBUTING.md for the short guide on adding a new buddy.

License

MIT. See LICENSE.