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

K
Kaspersky official blog
T
Threat Research - Cisco Blogs
N
News and Events Feed by Topic
Hacker News: Ask HN
Hacker News: Ask HN
Project Zero
Project Zero
Application and Cybersecurity Blog
Application and Cybersecurity Blog
博客园 - 叶小钗
Security Latest
Security Latest
Spread Privacy
Spread Privacy
aimingoo的专栏
aimingoo的专栏
N
News and Events Feed by Topic
Webroot Blog
Webroot Blog
U
Unit 42
Cyberwarzone
Cyberwarzone
小众软件
小众软件
Scott Helme
Scott Helme
Engineering at Meta
Engineering at Meta
Microsoft Security Blog
Microsoft Security Blog
T
The Blog of Author Tim Ferriss
A
About on SuperTechFans
爱范儿
爱范儿
S
Schneier on Security
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
Schneier on Security
Schneier on Security
Latest news
Latest news
GbyAI
GbyAI
cs.CV updates on arXiv.org
cs.CV updates on arXiv.org
Simon Willison's Weblog
Simon Willison's Weblog
The Register - Security
The Register - Security
WordPress大学
WordPress大学
博客园_首页
Blog — PlanetScale
Blog — PlanetScale
PCI Perspectives
PCI Perspectives
Jina AI
Jina AI
AI
AI
NISL@THU
NISL@THU
I
Intezer
G
GRAHAM CLULEY
B
Blog
S
Secure Thoughts
IT之家
IT之家
宝玉的分享
宝玉的分享
Recent Announcements
Recent Announcements
Y
Y Combinator Blog
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
酷 壳 – CoolShell
酷 壳 – CoolShell
有赞技术团队
有赞技术团队
V2EX - 技术
V2EX - 技术
Recorded Future
Recorded Future
Hacker News - Newest:
Hacker News - Newest: "LLM"

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 - narghev/askdiff: Ask your AI questions about its own code changes — from a Git diff viewer.
narghev · 2026-05-05 · via Hacker News: Show HN

npm version CI License: MIT

Treat your AI as a coworker — ask questions about its changes in the same session that wrote the code.

/askdiff from inside any Claude Code session opens a GitHub-style diff viewer in your browser. Hover a line, click +, type a question. The answer streams back inline — and because each ask resumes the same Claude Code session that wrote the code, the model already remembers the file, the conversation, and why it made the change.

askdiff demo

Quickstart

# 1. One-time skill install
npx -y askdiff install-skill

# 2. From any Claude Code session
/askdiff

That's it. No API key, no global install, no config. The browser opens to a syntax-highlighted diff of your working tree; comments stream back as the model thinks.

Why askdiff?

Developers often prompt AIs to write the code, then, if the diff becomes large enough, open draft GitHub PRs in order to review it better. Then, if there are any questions, take the diff back to the terminal, ask questions about it, and repeat.

Askdiff simplifies this process by combining the diff viewer and the Q&A interface into one seamless experience, directly integrated with the very same Claude Code session that wrote the code. It makes you treat the model truly as a coworker who already knows the entire context and the reasoning behind every single line of the diff.

How it works

Each ask spawns the claude CLI with --resume <your-session-id>. So your question becomes a real turn in the running session's transcript:

  • No diff sent to the model. The resumed session already has the full context that wrote the code; the prompt is just your question.
  • No Anthropic API key needed. askdiff doesn't talk to the API — it shells out to the claude CLI you've already auth'd via subscription or whatever.
  • No process cleanup. The server self-exits after 5 minutes of inactivity — close the browser tab and forget about it.

Features

Inline comments Click the + gutter button to comment on any line. Drag to comment on a range.
Streaming answers Tokens stream in as Claude generates them — same model context that wrote the code.
Threaded discussions Multiple asks per line, each its own thread, all anchored to the diff.

Inline comments

Hover any line in the diff. A + button appears in the gutter. Click it for a single-line question, or click and drag to range over multiple lines. The comment widget renders below the selected lines; type a question and hit Cmd/Ctrl+Enter (or click Send).

Streaming answers

Tokens stream in as the model generates them — usually starting within ~1 second, typing speed-of-thought. Click Stop mid-stream to abort. Markdown is rendered live, including syntax-highlighted code blocks in any of 30+ languages.

Threaded discussions

Each line can have multiple ask/answer pairs. They render as a threaded conversation inline with the diff, so you can ask a follow-up without losing context.

Configuration

All optional. Set as env vars before running npx -y askdiff — or let the skill resolve them automatically.

Variable Default Notes
PORT 7837 Auto-bumps if taken.
ASKDIFF_SESSION_ID (resolved from $PPID) Force a specific Claude Code session UUID.
ASKDIFF_PROJECT_CWD (parent CC manifest, then process.cwd()) Project directory to diff.
ASKDIFF_MODEL (inherits resumed session's model) Override the Claude model for asks.
CLAUDE_CONFIG_DIR ~/.claude Where Claude Code stores sessions/, projects/.

CLI flags also work (askdiff --port 7838 --no-open --session <uuid>). Run askdiff --help for the full list.

Updating

When you next run /askdiff and a newer version is on npm, the skill prints UPDATE_AVAILABLE: pinned=X latest=Y and asks whether to upgrade or proceed. Upgrade is one command:

npx -y askdiff@latest install-skill --force

This rewrites the skill to pin to the new version. The first subsequent /askdiff runs the upgraded CLI.

Skills shipped

install-skill writes one file: ~/.claude/skills/askdiff/SKILL.md. That's the entire surface area in your CC config.

In this repo (for contributors) there are two more:

  • /askdiff-dev — local Vite dev server with HMR + tsx-run WS server. Use when editing packages/ui-browser.
  • /askdiff-stop — kill everything /askdiff and /askdiff-dev started.

Architecture

The npm package (packages/cli) is a single esbuild-bundled Node binary that hosts an HTTP server (serving the prebuilt UI bundle in dist/ui/) and a WebSocket on the same port at /ws. The CLI imports startServer from @askdiff/server, which spawns claude --resume per ask and forwards text_delta events to the client. The browser UI (packages/ui-browser) is React 19 + Vite + Tailwind v4 + zustand, with react-diff-view for rendering and refractor for syntax highlighting.

Development

git clone https://github.com/narghev/askdiff
cd askdiff
pnpm install
pnpm test
pnpm lint
pnpm run build

From a Claude Code session in this repo:

/askdiff-dev                    # Vite + WS server with HMR
/askdiff-stop                   # tear it down

To exercise the production-shaped binary locally:

pnpm run build
node packages/cli/dist/index.js --port 7838

Troubleshooting

"Claude session: (none — set ASKDIFF_SESSION_ID or use --session)" The skill couldn't read the parent CC manifest. You're either running askdiff from outside a Claude Code session (no $PPID.json in ~/.claude/sessions/), or CLAUDE_CONFIG_DIR points somewhere else. Pass --session <uuid> explicitly to override.

"Port 7837 is already in use" Another askdiff is running, or something else grabbed the port. Run /askdiff-stop (in-repo), or pass --port 7838.

Browser opens, UI loads, but never connects The WS upgrade is failing. Check /tmp/askdiff.log — usually it's an old version of the UI cached against a new server (run /askdiff-stop and reload the browser tab) or a hung claude --resume subprocess (check ps aux | grep claude).

/askdiff doesn't appear in Claude Code's skill picker Run npx -y askdiff install-skill to write ~/.claude/skills/askdiff/SKILL.md. If it's there but still missing, restart Claude Code or run /reload-plugins.

License

MIT © narghev