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

Recorded Future
Recorded Future
爱范儿
爱范儿
Y
Y Combinator Blog
cs.CV updates on arXiv.org
cs.CV updates on arXiv.org
腾讯CDC
罗磊的独立博客
阮一峰的网络日志
阮一峰的网络日志
Know Your Adversary
Know Your Adversary
P
Proofpoint News Feed
T
Tailwind CSS Blog
Attack and Defense Labs
Attack and Defense Labs
G
GRAHAM CLULEY
大猫的无限游戏
大猫的无限游戏
博客园 - Franky
C
Cyber Attacks, Cyber Crime and Cyber Security
T
The Blog of Author Tim Ferriss
T
The Exploit Database - CXSecurity.com
博客园 - 叶小钗
Latest news
Latest news
H
Hackread – Cybersecurity News, Data Breaches, AI and More
The Hacker News
The Hacker News
量子位
S
Security @ Cisco Blogs
Microsoft Security Blog
Microsoft Security Blog
Stack Overflow Blog
Stack Overflow Blog
美团技术团队
GbyAI
GbyAI
Google DeepMind News
Google DeepMind News
IT之家
IT之家
U
Unit 42
Project Zero
Project Zero
B
Blog
博客园 - 【当耐特】
D
DataBreaches.Net
CTFtime.org: upcoming CTF events
CTFtime.org: upcoming CTF events
Hugging Face - Blog
Hugging Face - Blog
宝玉的分享
宝玉的分享
The Register - Security
The Register - Security
F
Full Disclosure
Vercel News
Vercel News
NISL@THU
NISL@THU
AWS News Blog
AWS News Blog
MongoDB | Blog
MongoDB | Blog
小众软件
小众软件
T
Threatpost
Martin Fowler
Martin Fowler
Engineering at Meta
Engineering at Meta
T
Tor Project blog
M
MIT News - Artificial intelligence
V
V2EX

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 - ibm777p2/Intelligence-Emotions: Intelligence Emotions — a PQ-based coaching skill stack for Claude Code
ibm777p2 · 2026-06-13 · via Hacker News: Show HN

Your mind is your best friend — and, left unsupervised, your worst critic.

Intelligence Emotions turns Claude Code into your personal mental-fitness team, built on the Intelligence Emotions model. Five coaches, one practice: catch the ten saboteurs (led by the Judge — the inner voice that finds fault with everything), do PQ reps (10-second shifts of attention to a physical sensation), and let the Sage choose the response. The team remembers between sessions — a private, local-only journal that makes every coach smarter about your actual patterns.

This is not therapy or medical care. The coaches say so themselves, once, plainly — and they know when to stop coaching and point you to a professional instead.

Who this is for:

  • Anyone building mental fitness who wants the practice to actually happen daily
  • First-time practitioners — structured coaching instead of a blank journal
  • People with a challenge they keep circling — a habit, a conflict, a decision that won't resolve

Quick start

  1. Install Intelligence Emotions (30 seconds — see below)
  2. Run /sage-session — bring one real challenge
  3. Run /intercept the next time a thought stings
  4. Run /pq-retro tonight before closing the laptop
  5. Run /pq-score after three days of journal data
  6. Stop there. You'll know if this is for you.

Install — 30 seconds

Requirements: Claude Code, Git, Bun v1.0+

Step 1: Install on your machine

Open Claude Code and paste this. Claude does the rest.

Install Intelligence Emotions: run git clone --single-branch --depth 1 https://github.com/YOUR-GITHUB-USERNAME/intelligence-emotions.git ~/.claude/skills/pq && cd ~/.claude/skills/pq && ./setup then add an "Intelligence Emotions" section to CLAUDE.md that lists the available skills: /pq, /sage-session, /intercept, /saboteur-scan, /sage-perspective, /navigate-review, /pq-retro, /daily-pipeline, /growth-spec, /commit, /pq-score, /habit-watch, /life-design, /saboteur-audit, /insight-doc, /second-coach, /context-save, /context-restore — and says that /pq is the front door when unsure which to use.

(The skills use the pq prefix — your mental-fitness quotient, the percentage of time your mind serves you rather than sabotages you.)

Step 2: First session

Bring something real — a challenge with weight, however half-formed. The Sage takes it from there.

See it work

You:  /intercept my coworker got promoted and I feel worthless

Spotter:  That word "worthless" — let's trace where it came from.
          What's the actual sentence running in your head, word for word?

You:  "she's two years younger and already ahead of me"

Spotter:  Two patterns in that sentence. The comparison clock — that's the
          Hyper-Achiever (the pattern that pegs your worth to external
          scorekeeping). And "worthless" is the Judge delivering the verdict.
          The lie: her promotion is a measurement of you. It feels like data.
          It's machinery — the same machinery would have produced the same
          sentence about whoever got promoted.

          Next time a promotion email lands — anyone's — ten seconds on your
          feet on the floor before your mind gets the microphone.
          Want me to log this interception?

The practice

The daily loop, as a team:

Time Command Coach What happens
Morning /daily-pipeline The Trainer One intention, a saboteur forecast for the day's terrain, first rep
In the moment /intercept The Spotter Trace a stinging thought: trigger → saboteur → the lie → the need. Rep prescribed, interception logged
Evening /pq-retro The Witness Five minutes: what triggered, what got caught, rep count, one Sage win. Writes the journal
Anytime /sage-session The Sage The flagship — any life challenge, walked through all five Sage powers

The 21-day arc, when something deserves real practice:

Step Command What happens
1 /growth-spec A vague intention ("be more patient with my kids") becomes a concrete 21-day practice: trigger inventory, daily reps anchored to real moments, check-ins
2 /habit-watch Scheduled look-ins; catches drift while the fix is still one sentence
3 /commit Day 21: the honest review, the closing entry, the commitment marked. No grades — what happened, what it taught, what's next

Which coach should I ask?

Situation Command
A whole situation with weight /sage-session
One specific moment that stung /intercept
"Check this draft/entry before I send it" — no fixes wanted /saboteur-scan
A decision I keep flip-flopping on /sage-perspective
"Will this plan actually stick?" /navigate-review
"Map all my patterns" — the wide view /saboteur-audit
"How am I doing?" — numbers from real data /pq-score
Design my mornings / environment from scratch /life-design
Something just clicked — keep it /insight-doc
"Push back on me harder" /second-coach
Not sure /pq

Power tools

Your data, on the command line (all local, all yours):

~/.claude/skills/pq/bin/pq-journal-search --days 7           # this week's interceptions, entries, commitments
~/.claude/skills/pq/bin/pq-journal-search --stats --days 7   # per-day reps, interception rate, saboteur tallies
~/.claude/skills/pq/bin/pq-journal-log saboteurs '{...}'     # log an interception by hand
~/.claude/skills/pq/bin/pq-journal-log entries --redact <id> # forget a record — expunged completely, archive included
~/.claude/skills/pq/bin/pq-config list                       # your preferences (name, rep_target, cadence, explain_level)

The journal is event-sourced and append-only: three streams under ~/.pq/journal/ (entries.jsonl, saboteurs.jsonl, commitments.jsonl), supersede-don't-delete, redact-on-demand. A write-time guard refuses credential-shaped secrets. /pq-score and /saboteur-audit read this data — nothing is ever estimated.

Uninstall

Option 1: Run the uninstall script

~/.claude/skills/pq/setup --uninstall

Removes the skill symlinks. Your journal and config in ~/.pq are never touched — that data is yours, including after you leave.

Option 2: Manual removal

# 1. Remove the skills
rm -rf ~/.claude/skills/pq
for s in pq sage-session intercept saboteur-scan sage-perspective navigate-review \
         pq-retro daily-pipeline growth-spec commit pq-score habit-watch life-design \
         saboteur-audit insight-doc second-coach context-save context-restore; do
  [ -L ~/.claude/skills/$s ] && rm ~/.claude/skills/$s
done

# 2. Only if you also want your journal gone (irreversible — it's your history):
# rm -rf ~/.pq

Docs

  • CLAUDE.md — contributor guide: the pipeline, the iron rules, how to write a skill
  • ETHOS.md — the operating philosophy: label don't fight; ten seconds at a time; every setback is a gift; the coach is never the Judge
  • CHANGELOG.md — versions, starting fresh at 1.0.0.0

Privacy

There is no telemetry. None, not opt-out — none exists. Everything personal lives in ~/.pq/ with owner-only permissions (0700 directories, 0600 files), never pushed to any remote, never sent to any service. Redaction is honored absolutely: ask any coach to forget something and the record is expunged from the live log and the archive. The test suite enforces that no external sink can quietly appear.

Troubleshooting

  • Skills don't show up in Claude Code — re-run ~/.claude/skills/pq/setup; check that ~/.claude/skills/sage-session is a symlink pointing into the install.
  • bun: command not found — install Bun, then re-run ./setup.
  • A coach sounds like the Judge — that's a bug in the product, not a feature of honesty. Open an issue with the transcript line; the anti-Judge rule is the product.

Intelligence Emotions

Exactly 10 saboteurs. Exactly 5 Sage powers. Never an invented eleventh or sixth — the test suite enforces the canon. The team: the Sage (lead coach), the Spotter (pattern recognition), the Trainer (rep drills), the Navigator (plans and direction), the Witness (reflection). One rule outranks everything they say: no coach is ever the Judge.

License

MIT — see LICENSE.