ๆƒฏๆ€ง่šๅˆ ้ซ˜ๆ•ˆ่ฟฝ่ธชๅ’Œ้˜…่ฏปไฝ ๆ„Ÿๅ…ด่ถฃ็š„ๅšๅฎขใ€ๆ–ฐ้—ปใ€็ง‘ๆŠ€่ต„่ฎฏ
้˜…่ฏปๅŽŸๆ–‡ ๅœจๆƒฏๆ€ง่šๅˆไธญๆ‰“ๅผ€

ๆŽจ่่ฎข้˜…ๆบ

Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
Application and Cybersecurity Blog
Application and Cybersecurity Blog
T
Threat Research - Cisco Blogs
Latest news
Latest news
Project Zero
Project Zero
TaoSecurity Blog
TaoSecurity Blog
Cyberwarzone
Cyberwarzone
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
Google DeepMind News
Google DeepMind News
P
Privacy & Cybersecurity Law Blog
T
Troy Hunt's Blog
cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
AWS News Blog
AWS News Blog
Hacker News: Ask HN
Hacker News: Ask HN
S
Security @ Cisco Blogs
C
Cisco Blogs
Help Net Security
Help Net Security
I
Intezer
W
WeLiveSecurity
Exploit-DB.com RSS Feed
Exploit-DB.com RSS Feed
่…พ
่…พ่ฎฏCDC
S
Secure Thoughts
MyScale Blog
MyScale Blog
Recorded Future
Recorded Future
G
GRAHAM CLULEY
L
LINUX DO - ็ƒญ้—จ่ฏ้ข˜
A
About on SuperTechFans
C
CXSECURITY Database RSS Feed - CXSecurity.com
ITไน‹ๅฎถ
ITไน‹ๅฎถ
J
Java Code Geeks
The Hacker News
The Hacker News
้˜ฎไธ€ๅณฐ็š„็ฝ‘็ปœๆ—ฅๅฟ—
้˜ฎไธ€ๅณฐ็š„็ฝ‘็ปœๆ—ฅๅฟ—
Scott Helme
Scott Helme
Recent Announcements
Recent Announcements
AI
AI
Cisco Talos Blog
Cisco Talos Blog
B
Blog RSS Feed
V
Vulnerabilities โ€“ Threatpost
C
Check Point Blog
Security Latest
Security Latest
S
SegmentFault ๆœ€ๆ–ฐ็š„้—ฎ้ข˜
T
The Exploit Database - CXSecurity.com
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
M
MIT News - Artificial intelligence
T
The Blog of Author Tim Ferriss
Attack and Defense Labs
Attack and Defense Labs
PCI Perspectives
PCI Perspectives
Recent Commits to openclaw:main
Recent Commits to openclaw:main
T
Tailwind CSS Blog
Apple Machine Learning Research
Apple Machine Learning Research

Hacker News: Show HN

PurrrrrFocus: Pomodoro Timer App - App Store Workflow Engine โ€” 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 โ†’ oscilloscope โ†’ verification with Claude Code โ€” Lucas Gerads Show HN: VCoding โ€“ 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 agentsโ€“no Airbnb, 0% commission GitHub - basteez/jsf-autoreload: maven plugin to enable hot reload on jsf projects uvm32/hosts/host-gdbstub at main ยท 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: ๐Ÿ“„ 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 โ€“ 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 LinkedInโ„ข ่ŒไฝๆŠ“ๅ–ๅทฅๅ…ท - Chrome ๅบ”็”จๅ•†ๅบ— GitHub - EdoardoBambini/Agent-Armor-Iaga: AI agents are getting tool access โ€” 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 โ€” Week 15, Apr 7โ€“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 Anthropicโ€™s Mythos harness to locate C/C++ memory vulnerabilities Show HN: OpenParallax: OS-level privilege separation for AI agent execution Hacker News Sorted - Chrome ๅบ”็”จๅ•†ๅบ— 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 ๅบ”็”จๅ•†ๅบ— 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 โ€” Safari browser automation via safari-mcp by achiya-automation ยท Pull Request #212 ยท 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 ๅบ”็”จๅ•†ๅบ— 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: ๐ŸŒฑ 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 systemsโ€”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 โ€“ A Python decorator that proves your code using Lean and LLMs Show HN: Pardonned.com โ€“ 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 โ€“ A self-improving agent framework built on LangGraph GitHub - stef41/vibescore: ๐ŸŽต Grade your vibe-coded project. One command, instant letter grade across security, quality, dependencies, and testing. GitHub - stef41/lmscan: ๐Ÿ” 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 ๅœจ Steam ไธŠ่ดญไนฐ FriedrichAI: Offline AI ็ซ‹็œ 10% GitHub - atripati/ark: AI Runtime Kernel โ€” a context operating system for AI agents. Eliminates tool bloat, loads only whatโ€™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 - raiyanyahya/kit: ๐Ÿต๏ธ Editor, Browser, Mail, Terminal, Agents. AI at the center.
RaiyanYahya ยท 2026-05-03 ยท via Hacker News: Show HN

Electron Node License Platform CI Tests GitHub Release

Your entire dev environment. One window. AI woven through everything.

Kit is not another Electron wrapper with a chat sidebar. It's a ground-up rethink of what a developer workspace looks like when AI is not a feature you reach for but the nervous system connecting every tool you already use. The editor, browser, terminal, git, email, calendar, whiteboard and an autonomous agent all share context. Nothing is siloed. Everything talks to everything.

Built by a developer who got likes to build things.

Kit workspace


Why Kit?

Every developer workflow is secretly the same. You write code in one window, look up docs in another, run commands in a third, manage git in a fourth and your AI assistant lives in a fifth tab that knows nothing about any of the others. The context switching is relentless and the cost is invisible until you add it up.

Kit is built on one idea: the workspace should think with you, not just sit there. When you open a file the AI knows. When you browse a doc the AI can read it. When you give the agent a task it uses your actual project not a blank slate. The tools aren't just co-located. They're connected.

It's also built to be extended. The agent tool system is explicit and composable. The pipeline runner is modular. The project rules system lets any codebase teach Kit how to behave. Fork it, extend it, wire in whatever you need. The architecture stays out of your way.


๐Ÿ”ฉ What's inside

โœ๏ธ Code Editor

A full editor built on CodeMirror 6 which is the same engine powering CodeSandbox, Replit and the next generation of browser-based IDEs. Syntax highlighting works out of the box for every major language. Multi-tab support means you work across files without closing anything. Font size, tab width and line wrap are all configurable. A dirty-state dot on each tab tells you what's unsaved at a glance.

Auto-save runs on a configurable interval. Session restore means you reopen Kit and pick up exactly where you left off with the same files and tabs. Markdown live preview opens a draggable split pane that hot-reloads as you type. F12 jumps to definition for any symbol in your file. Ctrl+Shift+P opens the command palette for everything else including opening files, triggering AI actions and toggling settings without touching the mouse.

The status bar runs three AI actions on the current file without leaving the editor:

Summarise reads the file and explains what it does in plain English covering key functions, inputs, outputs and dependencies.

Check for errors does a strict code review pass looking for bugs, edge cases, security pitfalls and style issues with line numbers on everything it finds.

Generate tests writes comprehensive unit tests including setup and teardown, edge cases, mocks and picks the right testing framework for the language automatically.


๐ŸŒ Browser

A real Chromium browser inside the workspace. Not a webview wrapper but a full browser with an address bar, tab bar, navigation history and bookmarks. Use it for docs, research, localhost, web apps or anything you'd normally open Chrome for.

The browser toolbar has four AI-powered actions built in. Summarise page reads the full text of whatever you're looking at and opens a clean summary in a detached window. Extract text pulls the raw readable text from the page so you can copy it or feed it into something else. Screenshot captures the current page as an image and opens it in a result window. Bookmark saves the current tab with its favicon to your sidebar so you can get back to it without searching.

The AI in the terminal also reads the page you're currently browsing as live context. You can ask it a question about the docs you have open without copying anything. The browser and the AI are genuinely aware of each other.


๐Ÿ’ป Terminal

A full terminal where every system command runs exactly as it would anywhere else. git push, npm install, docker compose up, python train.py โ€” anything your shell can do. Output streams line by line as it arrives so long-running processes show progress in real time. Ctrl+C kills any running process including nested ones.

Type help to see everything available.

Navigation and files

pwd                     Show current directory
cd <path>               Change directory
ls [path]               List files
open <file>             Open file in editor  (also: e, edit, vi)
close                   Close current file

Environment

export VAR=value        Set environment variable
unset VAR               Remove environment variable
env VAR                 View environment variable

AI with full context

/ai <prompt>                    Ask anything โ€” AI sees your open file, browser page, calendar and bookmarks
/ai <prompt> --file             Include the current file as context
/ai <prompt> --path <p>         Include files from a specific path
/ai <prompt> --model <name>     Use a specific model for this request

Code generation and review

/ai code <description>          Generate code from a description
/ai complete --file             Complete the current function or class
/ai explain --file              Plain-English explanation of the current file
/ai fix <error> --file          Fix a specific bug or error
/ai test --file                 Generate unit tests
/ai refactor --file             Improve structure without changing behaviour
/ai optimize --file             Optimise for performance
/ai document --file             Generate documentation
/ai review --file               Full code review with suggestions
/ai convert <language> --file   Convert the file to another language

The AI in the terminal has full conversation memory for the session. It remembers what you said earlier, what file you had open and what you were browsing. You can switch models mid-conversation with --model. Every request is context-aware by default so the AI already knows your working directory, open file, browser URL, calendar events and saved bookmarks without you having to mention any of it.

Models update automatically when new versions of the app are released.


๐Ÿ”€ Git Panel

A full visual git interface so you don't need the terminal for the common path. You can see your current branch, commit SHA, modified files, untracked files and how far ahead or behind the remote you are. Stage individual files or everything at once with a checkbox, write your commit message, commit, pull and push all from a modal you open by clicking the git badge in the status bar.

The git badge updates every 3 seconds and shows real state including branch name, short SHA, ahead/behind count, modified file count and untracked file count. It only runs when you're inside a git repository so there's no background noise anywhere else.


๐Ÿค– Kit Agent

An autonomous AI agent you give tasks to in plain English. Not a chat window and not autocomplete. An actual agent that thinks, plans and acts in a loop with tools until the task is done.

Tell it "Scaffold a REST API with authentication in Express, add rate limiting and write tests" and it creates every file, installs the dependencies, writes the code and tells you what it built.

Tell it "Find all the TODO comments across this project, group them by urgency and write a summary" and it searches every file, reads the results and gives you a structured report.

Tell it "The auth token isn't expiring correctly in auth.js, read it, find the bug and fix it" and it reads the file, locates the issue, writes the fix and explains the change.

The five tools the agent uses autonomously:

Tool What it does
read_file Read any file โ€” always runs silently
write_file Write or overwrite a file โ€” asks permission first
list_dir List directory contents โ€” always runs silently
run_command Execute any shell command โ€” asks permission first
search_project Full-text grep across the project โ€” always runs silently

Before any file write or shell command runs Kit shows you exactly what the agent is about to do and gives you three choices. Allow once runs this specific action and asks again next time. Allow all blanket-approves this type of action for the rest of the session. Deny skips it and the agent adapts. Permissions reset at the start of every new task so you're always in control.

Drop a .kitrules or AGENT.md file into any project folder and the agent reads it at the start of every task. Put your coding conventions, architecture decisions, what not to touch and preferred libraries in there. The agent follows them without being told twice.

Works with OpenAI and Anthropic. Models update automatically when new versions of the app are released.


๐Ÿชœ Stairs โ€” Workflow Automation

A visual pipeline builder for turning repetitive multi-step work into one-click automations. Build a workflow once, name it and run it whenever you need it.

You can chain four step types in any order. AI sends a prompt to any model and you can reference the previous step's output with {{prev_step.output}}. Shell runs any command and pipes outputs between steps. HTTP makes GET, POST, PUT, PATCH or DELETE requests with optional JSON body and headers. File reads, writes or appends to any file on disk.

Each step shows its output inline as it runs and you can stop mid-run if something looks wrong. Every step output feeds the next so the whole pipeline is connected.

Some things you could build: fetch data from an API then summarise it with Claude then write it to a daily report file. Or run your test suite then if there are failures draft an incident summary and write it to a log. Or read a log file then ask the AI to find anomalies then append the findings to a briefing.


๐ŸŽจ Whiteboard

A freehand drawing canvas for when you need to think in shapes instead of text. Sketch an architecture, map out a flow or just work through an idea visually. It's one keystroke away with Ctrl+W and one keystroke back.

You get a pen, rectangles, ellipses, arrows, text, sticky notes, image upload, an eraser and select and move. Mind map mode lets you build connected node trees for brainstorming. There's a colour picker for every element and undo/redo with Ctrl+Z and Ctrl+Y. The board auto-saves so it's there when you come back and you can export it as a screenshot any time.


๐Ÿ“ Sidebar and Starred Folders

The sidebar shows your project file tree and updates live as files change. Hover any folder and star it to make it your default landing directory. The next time you open Kit the terminal, sidebar and git panel all open there automatically. One click on the star button in the toolbar jumps back to it from anywhere.

Bookmarks from the browser live in the sidebar too with favicons so you can get back to saved URLs without switching modes.


๐Ÿ” Project Search

Ctrl+K opens full-text search across your entire project searching both file names and file contents at the same time. Results appear as you type. Use arrow keys to navigate and Enter to open which jumps directly to the matching line in the editor. No configuration, no indexing and no waiting.


๐Ÿ“ง Email

A full IMAP/SMTP email client you configure once and it works with Gmail, Fastmail, Outlook or any standard provider. Read threads, reply, compose, send, mark as read and move to trash without leaving your workspace.


๐Ÿ“… Calendar

A local event manager where you create events, set dates and times and see what's coming. Everything is stored in ~/.Kit/calendar.json with no accounts, no sync and no cloud. Your schedule lives in the same window as your work and the AI can see it as context when you're asking questions.


๐Ÿ”Œ Built to be extended

Kit is designed to grow. Adding a new agent tool means writing one case in a switch and registering it. The Stairs step runner is modular by design. Project rules mean the agent adapts to any codebase without touching source code.

The surface area is intentionally small. Fork it, add a tool, wire in a new AI provider, build a new step type for Stairs. The architecture gets out of your way.


โŒจ๏ธ Keyboard shortcuts

Shortcut Action
Ctrl+K Project search
Ctrl+S Save file
Ctrl+D Toggle dark / light theme
Ctrl+E Toggle sidebar
Ctrl+B Browser
Ctrl+W Whiteboard
Ctrl+M Email
Ctrl+0 Back to editor
Ctrl+Shift+A Kit Agent
Ctrl+Shift+R Stairs
Ctrl+Shift+P Command palette
F12 Jump to definition
Ctrl+Z Undo (whiteboard)
Ctrl+Y Redo (whiteboard)

๐Ÿš€ Install

Download the latest release from the Releases page.

macOS โ€” download the .dmg, open it, drag Kit to Applications and run it.

Linux โ€” download the .AppImage, make it executable and run it:

chmod +x Kit-*.AppImage
./Kit-*.AppImage

On first launch click the key icon in the status bar and add your OpenAI or Anthropic API key. Everything else is already there.


๐Ÿ›  Build from source

git clone https://github.com/raiyanyahya/Kit.git
cd Kit
npm install
npm start

๐Ÿ—‚๏ธ Workspace

~/.Kit/
โ”œโ”€โ”€ projects/        agent-created projects
โ”œโ”€โ”€ notes/           text notes and documents
โ”œโ”€โ”€ data/            data files and datasets
โ”œโ”€โ”€ scratch/         quick experiments
โ”œโ”€โ”€ boards/          whiteboard saves
โ”œโ”€โ”€ stairs/          saved workflows
โ””โ”€โ”€ calendar.json    calendar events

Kit is for developers who want their tools to think with them.

If Kit is useful to you a โญ goes a long way and helps more people find it.


mandala icon by Icons8