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

云风的 BLOG
云风的 BLOG
P
Privacy International News Feed
Vercel News
Vercel News
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
博客园 - 叶小钗
F
Fortinet All Blogs
Security Archives - TechRepublic
Security Archives - TechRepublic
L
LINUX DO - 最新话题
AWS News Blog
AWS News Blog
Engineering at Meta
Engineering at Meta
Attack and Defense Labs
Attack and Defense Labs
Recent Announcements
Recent Announcements
Recent Commits to openclaw:main
Recent Commits to openclaw:main
PCI Perspectives
PCI Perspectives
Cloudbric
Cloudbric
AI
AI
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
IT之家
IT之家
Exploit-DB.com RSS Feed
Exploit-DB.com RSS Feed
J
Java Code Geeks
M
MIT News - Artificial intelligence
Cisco Talos Blog
Cisco Talos Blog
V2EX - 技术
V2EX - 技术
Webroot Blog
Webroot Blog
Microsoft Security Blog
Microsoft Security Blog
Cyberwarzone
Cyberwarzone
博客园 - 聂微东
G
Google Developers Blog
W
WeLiveSecurity
罗磊的独立博客
P
Privacy & Cybersecurity Law Blog
阮一峰的网络日志
阮一峰的网络日志
A
About on SuperTechFans
WordPress大学
WordPress大学
The GitHub Blog
The GitHub Blog
T
Tailwind CSS Blog
V
Visual Studio Blog
Application and Cybersecurity Blog
Application and Cybersecurity Blog
H
Hackread – Cybersecurity News, Data Breaches, AI and More
S
Secure Thoughts
Apple Machine Learning Research
Apple Machine Learning Research
Hugging Face - Blog
Hugging Face - Blog
Google DeepMind News
Google DeepMind News
Google DeepMind News
Google DeepMind News
雷峰网
雷峰网
cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
F
Full Disclosure
Blog — PlanetScale
Blog — PlanetScale
The Last Watchdog
The Last Watchdog
P
Proofpoint News Feed

Show HN

GitHub - flightdeckhq/flightdeck: Observability and control plane for AI agents. CSP Radar GitHub - Light-Heart-Labs/DreamServer: Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image generation. GitHub - Diplomat-ai/diplomat-agent-ts: What can your TypeScript AI agent do to the real world? Scan your code. See which tool calls have zero checks Code Block Selector - Visual Studio Marketplace Prometheus dependency graph — interactive showcase | Riftmap Show HN: I made a vi-like modal keyboard plugin for Figma GitHub - run-llama/liteparse: A fast, helpful, and open-source document parser GitHub - dalemyers/Roar: A macOS CLI tool for notifications GitHub - district-solutions/open-agent-tools-coder: Enables small-to-large self-hosted ai models to use local source code when running tool-calling agentic workloads. We actively data mine 20,900+ (2+ TB) popular github repos using large and small ai models to create reuseable: json, markdown and parquet files for local-first tool-calling models. GitHub - progapandist/stripeek: A local TUI proxy for real-time Stripe API debugging, built for navigating complex payloads fast. GitHub - sir1st/hermes-desktop: All-in-one cross-platform desktop app for Hermes Agent — bundles Python + hermes-agent + hermes-web-ui GitHub - astefanutti/shaderbang: Shebang for Shaders Show HN: Generate Claude Code Workflows using Spec Driven Development approach GitHub - nixys/nxs-universal-chart: The Helm chart you can use to install any of your applications into Kubernetes/OpenShift Show HN: AI agents for UK GDAD PCF roles and their skills The Two Pillars: Mixer Mode and Meta-Software in the Reorganization of Software Work After AI GitHub - JaiCode08/teleport-env What 1,000+ Harness Experiments Taught Me About Self-Improving Agents Show HN: Liiists, a Markdown-first, iOS and CLI list app SwiperTab – Get this Extension for 🦊 Firefox (en-US) GitHub - kouhxp/fftext: Summarize, explain, fact-check, or translate any text, URL, or file. No GPU. No cloud. One command GitHub - sweetpad-dev/sweetpad: Develop Swift/iOS projects using VSCode GitHub - dogmaticdev/IRON: IRON a.k.a. Intermediate Representation Object Notation is a Interpreter/Database that is used to create Programming Languages. GitHub - sjhalani7/vaen: Package your AI coding harness into a portable .agent file, and share it across repos, teams, & the community without ever having to copy-paste instructions, skills, MCP config, or secrets. Show HN: Gandalf the Grader Show HN: Citadeld – replay any CI failure locally from a single file GitHub - tdortman/cuSBF: High-Performance GPU Super Bloom Filter coral-ai/claude-code-token-xray at main · Coral-Bricks-AI/coral-ai GitHub - ulyssestenn/funes: Funes is a Git-based framework for LLM-managed knowledge work: an AI Librarian ingests raw sources, builds an interlinked Markdown knowledge base, and uses it to produce cited reports, analyses, and other outputs. GitHub - ThatXliner/gah: Git Add Hunk, built for agents to use GitHub - harmont-dev/harmont-cli: Command-line client for the Harmont CI platform GitHub - brooksmcmillin/mcp-authflow: OAuth 2.0 Authorization Server framework for MCP servers GitHub - javaid-codes/audit-supply-chain-agents GitHub - amorey/gochan: A small library of common channel architectures for Go, inspired by Rust GitHub - arifozgun/OpenGem: Free, Open-Source AI API Gateway with Gemini, OpenAI & Anthropic Compatibility in 1 file GitHub - Pranesh950/BioPetals: 🌸 Run BIOxAI models at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading GitHub - cnguyen14/bounty-doctor: Diagnose a GitHub bounty issue before you waste hours: detects honeypot scam repos, AI-bot attempt swarms, and stale contests. Show HN: CoreMCP – MCP Server for On-Prem DBs Show HN: KittyHTML – Render HTML/CSS as an inline image in your terminal GitHub - bingud/filemat: Web-based file manager Show HN: TruthLens – Free multi-signal deepfake image detector GitHub - apexlocal-jz/claude-usage-tray: Windows system-tray app showing your Claude Code rate-limit usage at a glance. Zero deps, ~300 lines of PowerShell. Cross-IDE (works regardless of VS Code, Cursor, plain terminal). Release v0.1.2.1 · kouhxp/yapsnap GitHub - noopolis/moltnet: Self-hostable chat network for AI agents. Pre-built bridges for Claude Code, Codex, and the Claws. Rooms, DMs, history. No Slack bots, no Matrix, no glue code. GitHub - tamerh/enju: Coordinating Humans, AI Agents, and Compute as Peers on a Shared Workflow Graph Show HN: Continuity-auth – Respect-weighted rate limits for the open web GitHub - luml-ai/luml: AI lifecycle platform where engineers and agents track experiments, train models, and ship to production. GitHub - mrdanielcasper/CoreTex: A UNIX-inspired, biomimetic, flat-file AI harness and knowledge engine. GitHub - clemg/pierre-github: Pierre's diffs.com and trees.software for Github GitHub - lyriks-io/unspaghettit: Behavior-driven AI development without prompt spaghetti. GitHub - sofumel/claude-handoff-revive: Resume Claude Code work after rate/usage/context limits without replaying the prior transcript. Auto-saves at 90%/95% usage. Plugin-installable, 10 languages. GitHub - dotexorg/saferpc: Typed, end-to-end encrypted RPC over any bidirectional channel. GitHub - BeeZeeAgent/beezee: Agent harness orchestration Legato Next.js Boilerplate for Internal Tools · CoreUI GitHub - clark-labs-inc/clark-hash: Clark Hash, 32x smaller searchable sketches for embeddings GitHub - ZeroPointRepo/youtube-mcp: The fastest YouTube transcript + YouTube search MCP for AI agents. Try for free. Typing Mastery — climb toward 100+ WPM, deliberately GitHub - Andebugulin/Awareen GitHub - fayzan123/claude-workflow-composer: Visual desktop app for composing multi-agent coding workflows. Drag agents, attach skills and MCPs, wire handoffs, export to .claude/ GitHub - harshaneel/humanize: Best static AI text humanizer. Two research-grounded skills that work in any LLM (Claude, ChatGPT, Gemini, Codex): humanize beats perplexity-based detectors, ai-check produces forensic scoring with evidence-quoted flags. Nine levers, 50+ peer-reviewed sources, 2024-2026 detection literature. GitHub - StackOneHQ/stack-nudge GitHub - nodes-app/swift-markdown-engine: A native AppKit Markdown editor for macOS, built on TextKit 2 and bridged to SwiftUI. We hardened an LLM agent. Each defense we added made it more exploitable. GitHub - alkait/WhatsKept: Agent-queryable WhatsApp history from an iOS backup — a single Go binary. GitHub - octelium/cordium: Open-source, general-purpose sandbox platform for devs and AI agents that provides identity-based secure access to infrastructure without credentials. WAR.GOV/UFO Microfilm5 GitHub - scosman/videowright: Build animated explainer videos with your coding agent GitHub - dipankar/dscode: The code editor you can take apart. GitHub - zoharbabin/web-researcher-mcp: MCP server (Go) for AI assistants: web search, content extraction, academic/patent/news research. Multi-provider routing, 4-tier scraping, search lenses. Works with Claude, Cursor, and any MCP client. GitHub - ruvnet/RuView: π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video. GitHub - scanaislop/aislop: Catch the slop AI coding agents leave in your code: narrative comments, swallowed exceptions, as-any casts, dead code, oversized functions. 50+ rules across 7 languages (TypeScript, JavaScript, Python, Go, Rust, Ruby, PHP). Sub-second, deterministic, no LLM at runtime. MIT-licensed. GitHub - kouhxp/cheap-im: CPU-only voice agent approximating Thinking Machines' Interaction Models demo GitHub - unprovable/OrchidMantis: Orchid Mantis — standalone framework for Zero-Knowledge Proofs of eXploit (ZKPoX). GitHub - MarcellM01/TinySearch: Shrink the web for your local LLMs! GitHub - pileax-ai/pileax: PileaX is an all-in-one AI knowledge base system. 🍀 GitHub - TangibleResearch/Halgorithem: A Algo designed to detect AI Hallucitions GitHub - DO-SAY-GO/freelang: I love freelang GitHub - CarpseDeam/Aura-IDE: An AI coding harness that shaped itself - Planner/Worker agents, repo awareness, surgical edits, validation, recovery, and safe diff approvals. GitHub - chojs23/concord: A feature-rich TUI client for Discord GitHub - tommyjepsen/awesome-ux-skills: UX & AI Product designs skills you can use today in Claude Code GitHub - aerf-spec/aerf: Agent Evidence Receipt Format (AERF) — an open specification for tamper-evident, independently verifiable records of AI agent actions. GitHub - kklimuk/docx-cli: CLI for AI agents (Claude, Codex) to read, edit, and comment on .docx files with full format fidelity. GitHub - Jwrede/tokentoll: Catch LLM cost changes in code review. Infracost for LLM spend. GitHub - samchon/ttsc: A `typescript-go` toolchain for compiler-powered plugins and type-safe execution + 500x faster lint integrated into compiler GitHub - Higangssh/homebutler: 🏠 Manage your homelab from chat. Single binary, zero dependencies. GitHub - olalie/tapmap: See where your computer connects and what stands out on a live world map. GitHub - matisiekpl/neond: DX-focused control plane for Postgres dedicated to non-critical workloads. Your postgres:latest replacement 🐘 GitHub - Diplomat-ai/diplomat-agent: What can your AI agent do to the real world? Scan your code. See which tool calls have zero checks GitHub - Bajusz15/beacon: Open-source agent for secure remote access, monitoring, and deploys across home-lab and self-hosted machines like Raspberry Pi, N100, or any Linux server. Open web based TTY or tunnel Home Assistant and other local services securely without opening ports. BigTech AI News - Chrome 应用商店 GitHub - vinhnx/VTCode: VT Code is an open-source coding agent with LLM-native code understanding and robust shell safety. Supports multiple LLM providers with automatic failover and efficient context management. GitHub - michaelaz774/decision-engine: A decision operating system for startup founders, powered by Claude Code. Synthesizes wisdom from 25+ legendary founders and investors into interactive AI-driven decision frameworks. GitHub - Chrilleweb/dotenv-diff: Validate environment variable usage in your codebase GitHub - Lumen-Labs/brainapi2: BrainAPI is a knowledge graph–powered AI memory layer that transforms unstructured data into structured knowledge, enabling intelligent search, recommendations, and contextual memory for AI agents and applications. GitHub - familiar-software/familiar: Let AI watch you work. Familiar lets your AI update its memory, skills, and knowledge by watching your screen. GitHub - skorotkiewicz/rudo: A small, elegant dock for Wayland GitHub - muxshed/shed: One stream in, or many. Every destination, simultaneously. No cloud middleman, no per-channel fees, no limits. make sidebar/address bar rounded corner toggleable
RainBreak - The AI doesn’t need a break. But you do.
Franz Enzenhofer · 2026-06-09 · via Show HN

// the relaxing rain break for macOS

A real workday screen - Hacker News and coding terminals - under falling rain

One keystroke turns your screen into calm rain and gives you a real break - 1 to 21 minutes. Your AI agents keep shipping while you breathe. A free macOS menu-bar app.

Take a short break. A rain break. A real one.

v0.2.1 · 3 MB · 97 downloads and counting

// why a rain break

AI agents made your Mac as addictive as a social feed.

Dopamine hits, infinite scroll, one more prompt - the same loop that makes social media so easy to love now lives in your terminal. Great for shipping. A lot for one human. A short rain break gives your head a moment to catch up, and you come back sharper.

You cannot out-work software that never sleeps. So stop trying. Out-rest it instead.

It’s not how hard you work. It’s whether you can stop.

// the research

Why are we suddenly so burned out from AI?

Not a vibe - a pattern. Straight from the threads:

Y Hacker News new | past | comments | ask | show | jobs

I feel tired working with AI much faster than I did when I used to code… I don’t even bother reading the code anymore. Manually coding engaged my brain much more and somehow was less exhausting.

When your AI does 8 things right and then confidently does the 9th wrong, you spend mental energy second-guessing everything. Supervising an unreliable system is more exhausting than just doing the task yourself.

I feel physically drained coming back from work and going to use more AI… it is exhausting keeping up. I would burn through a week’s worth of credits in a day.

Reviewing LLM-generated code is way more mentally draining… Productivity definitely went up, but my understanding of the codebase dropped fast.

Plenty of people find vibe coding mentally exhausting - not everyone wants to be a manager - and think LLMs suck the joy that was left in programming.

The science is catching up to the feeling. MIT wired 54 writers with EEG headsets: LLM users showed up to 55% lower brain engagement and the lowest sense of ownership of their own words - they call it cognitive debt. And 77% of workers using AI say it actually added to their workload.

Real comments, pulled from the Hacker News API. Links go to the originals.

// the honest catch

There is no skip button.

The break holds for the full time you set. No skip, no snooze. So for once you actually stop - and come back clearer, calmer, and faster than the version of you that never looked away.

That’s the value. A break you can’t talk yourself out of.

10 min

Across 22 studies, breaks of ten minutes or less measurably cut fatigue and lifted mood. Small pause, real recovery.

take a rain break

A break worth taking. One you can’t weasel out of.

01

Actually relaxing

Calm, full-screen rain that rises, holds, and softly settles - not a ticking timer bar. Somewhere to put your eyes down and let your shoulders drop.

02

Your agents don’t pause

The rain takes your screen, not your work. Claude Code and Codex keep running while you rest. You lose nothing by stepping away - that is the whole trick.

03

It holds

Keys, clicks, and scroll are gently blocked for the full break. No skip, no snooze, no “one more thing.” By design, the only early exit is a full shutdown.

04

Your rhythm, one keystroke

One, two, five, seven, twelve, or twenty-one minute breaks straight from the menu bar. A quick breather or a real pause - pick one and the rain takes over.

// the whole app

One menu. That’s the whole thing.

No dashboard, no settings maze. It lives in your menu bar - and this one is live: Start the Rain to rain on this page, Quit RainBreak to stop.

Three steps. Then it just runs.

  1. 1

    Install and launch

    A quick first-run setup, with rain already falling behind it.

  2. 2

    Work as usual

    RainBreak waits in the menu bar. Your agents run. The rain is one keystroke away.

  3. 3

    Take the break

    Pick a length. The screen turns to rain - and holds it until you are done.

40 sec

Even a 40-second glance away rebuilt attention and cut errors. Your break doesn’t have to be long - it has to be real.

get RainBreak, free

// free forever

RainBreak is free forever. Buying a license is optional.

The full app is free, with every feature, for as long as you use it. Want to buy a license? Cool. Want to keep using it for free? Also cool. A 4.99 EUR license is a thank-you that removes the in-app reminder and supports ongoing macOS releases. The key is verified offline on your Mac; no account, no subscription, no telemetry.

Already bought? Open RainBreak → Settings → License and paste the key from your email.

RainBreak app icon

Give yourself a real break.

Take a break. Take a RainBreak.

Download RainBreakfree · macOS 14+

v0.2.1 · 3 MB · signed DMG · 97 downloads and counting

  • Apple-notarized
  • Apple silicon
  • macOS 14+
  • No sign-up

// for the skeptic (hi)

It blocks your input. Here is exactly how - and what can’t go wrong.

How does it block the keyboard and mouse?
Through macOS’s normal input-monitoring APIs (a CGEventTap plus event monitors) - the same mechanism screen-time and accessibility tools use. No kernel extension, no driver, nothing that can wedge your Mac.

What if it crashes?
The block lives in the RainBreak process. If it ever crashes or is killed, the block dies with it and your Mac comes back instantly - you are never locked out by a bug, only by design.

And if I really need out of a break?
By default you wait it out - that is the point - or shut the Mac down. If you want a panic key, turn on the double-Esc emergency exit in Settings; it is off by default.

Is it spying on my screen?
No account, no telemetry, no servers. Everything runs locally on your Mac, and it is Apple-notarized so Gatekeeper has already checked it.