标签：#showdev

Last year I needed to ask for a raise. I knew my number, I'd read the guides, I had bullet points in my notes app. Then my manager said "let's chat about your goals for next quarter" and I said "sounds great, looking forward to it" and hung up. Never brought up money. Same thing kept happening elsewhere. Coworker taking credit for my work, I said nothing. Relationship that should've ended months earlier, I kept postponing. I always knew what to say. I just couldn't say it with someone actually looking at me. So I started building a thing to practice on. That thing became cosskill . What it actually is You pick a persona, tell it the situation in a sentence, and start talking. The persona doesn't help you. It holds position and pushes back. You practice not folding. Think of it as a flight simulator for hard conversations. You rehearse until your opener comes out steady, then go do the real thing. 20 personas across five categories: Operators (Musk, Jobs): first-principles thinking, harsh product feedback Strategists (Trump, Buffett): treat everything as a deal or a bet Relationship (Ex, Coworker): breakups, workplace friction, family money Philosophy (Socrates, Aurelius, Confucius, Sun Tzu, four more): each tradition frames problems differently Psychology (Rogers, Rosenberg, Ellis, Frankl, Kahneman, Jung): therapeutic frameworks on real situations These aren't celebrity impressions. The Buffett persona won't hype your startup idea. It'll ask "what's the downside?" and keep asking until you have something concrete. Tech stack Next.js 16 on Cloudflare Workers. DeepSeek for inference. Cloudflare D1 (SQLite at edge) for the bits that need to persist. No user accounts, chat history lives in localStorage. Monthly cost stays low enough that the free tier (10 messages/day) doesn't worry me. Why I made these choices DeepSeek instead of GPT-4/Claude. Each conversation is 10-30 messages. At GPT-4 pricing a free product bleeds money. DeepSeek gives maybe 90% of the quality for

GitHub - nikhilt101/email-blast-tool: Open source HTML email sender tool using CSV/XLSX + Gmail SMTP · GitHub Open source HTML email sender tool using CSV/XLSX + Gmail SMTP - nikhilt101/email-blast-tool github.com

How I Built a Bilingual AI-Powered Business Manager for Street Vendors in Jamshedpur The Problem Walk through any street in Jamshedpur, Jharkhand, and you'll find hundreds of small shop owners and hawkers running their entire business from memory — stock levels, daily sales, employee wages, profit margins. They have no tools. Notebooks get lost. Mental math fails. And at the end of the day, most don't even know if they made a profit. These vendors are not tech-illiterate. They have smartphones. They use WhatsApp. But every existing business app is either too complex, too expensive, or only available in English. I wanted to solve that. The Solution — Dukaan Manager Dukaan Manager is a free, offline-capable Progressive Web App (PWA) and Android app built for small shop owners and street vendors in India. It runs entirely in the browser — no server, no subscription, no data charges beyond the initial load. Built using HTML, CSS, JavaScript , and powered by the Gemini 2.0 Flash API , it gives every small vendor access to a smart business advisor in their pocket. What It Does 📦 Stock Management Vendors can add items by name or photo. Each item stores buying price, selling price, and quantity. The app automatically calculates profit margins and flags low-stock items with colour-coded alerts. 💰 Daily Sales Recording Sales are recorded item by item, linked to which employee made the sale. The app auto-fills prices and calculates the total. Unsaved drafts survive accidental page refreshes using sessionStorage. 👥 Employee Tracking Add employees with their role, salary, phone number, and joining date. Mark daily attendance (present/absent) with one tap. Track total sales made by each employee across all time. 📅 Sales History Every saved sale is stored permanently in the browser's localStorage. History is grouped by date, collapsible, and shows daily revenue and profit — clean and simple. 🤖 AI Business Advisor (Gemini-Powered) This is where Google AI comes in. Using the Gemini

I Built pretext-pdf: Serverless PDFs Without Chromium I got frustrated with PDF generation in Node.js. Every tool had trade-offs, and none of them felt right. The Problem Every time I needed to generate PDFs programmatically, I hit the same walls: Puppeteer — Renders HTML to PDF beautifully, but takes 500ms-2s per page. Way too slow for batch operations. wkhtmltopdf — Old, fragile, breaks in production, dependency hell. pdfmake — Good for simple invoices, falls apart with complex layouts. All of them — Overkill if you're not rendering HTML. And here's the kicker: I didn't need to render HTML. I had structured data (invoices, reports, certificates) that I needed to turn into PDFs programmatically . The Solution I built pretext-pdf — a JSON-based PDF generation library. Instead of: javascript // ❌ Puppeteer: render HTML const browser = await puppeteer.launch(); const page = await browser.newPage(); await page.setContent(html); const pdf = await page.pdf(); // 1000ms+ You do: // ✅ pretext-pdf: define structure const doc = { sections: [ { type: 'heading', text: 'Invoice' }, { type: 'table', rows: [...] } ] }; const pdf = await renderPDF(doc); // 40-100ms No Chromium. No external dependencies. Pure Node.js. Why This Matters If you're building: ✅ Invoice generation systems ✅ Dynamic reports for your SaaS ✅ AI agents that create PDFs (Claude, Cursor, Windsurf) ✅ Certificate systems ✅ Multi-language documents ...pretext-pdf is built for you. Today: v2.0.14 Launch I just shipped a major upgrade. The text layout engine (which handles how words break across lines) is now significantly better: Better CJK + Latin mixed-script handling Smarter punctuation (quotes stay with their text) 7-12% faster Zero breaking changes The Stats 337 tests passing — production-ready 0 critical vulnerabilities — secure MIT licensed — free to use Open source — contribute or fork Technical Foundation The layout engine is based on pretext by Cheng Lou (React core team). I cherry-picked 11 patches for

The conversation about who reads your website has been shifting. Agents are part of it now. ChatGPT fetches URLs. Perplexity reads content. Shopping agents try to complete purchases. Coding agents hit your API. Most of those products were built for humans, tested against humans. The agents showed up later and quietly. When they can't figure something out, they don't complain. They just bounce. I heard the phrase "second audience" at a hackathon where you.com was one of the hosts. It stuck. That's what agents are: a second audience the web wasn't designed for and isn't being measured against. And now, I want to build something about it. A scanner that tells you what an AI agent experiences when it tries to use your website or your API. The internal name is Perseus Clew and the public product is Agentis Lux. The split is intentional: Perseus Clew is the engine name, part of a suite of AI builder tools , and Agentis Lux is the product-facing name (Latin for "light of the agent") that describes what agent users see. This isn't a launch post. I just finished a docs phase, and I'm about to write code. Before I do, I want to put this in front of dev.to builders and find out what I'm missing. What it will do Three layers: Deterministic scanning. Twelve check categories — six for frontends, six for APIs — looking at HTML, ARIA, structured data, OpenAPI specs, error responses, idempotency patterns. Same input, same score, every time. The methodology will be published, the weights will be public, and anyone can audit it. AI-readiness scoring tools have a reputation for inflating numbers and hiding their methodology, so the trust floor is making everything inspectable. That's the foundation the rest sits on. An AI-written verdict. After the score, a Bedrock call reads the top findings and writes one sentence about what an agent experiences. Something like: "An agent visiting this page can read your product descriptions, but can't tell which button starts checkout, so it can't f

Every "what should I build" thread on here is full of AI wrappers fighting over the same five SaaS founders. Meanwhile there's a guy sitting at a loading dock right now, doing arithmetic in his head, who is about to undercharge his broker by a few hundred bucks because nobody built him a 30-second tool. I built that tool. It's a free detention-pay calculator for truck drivers. This is the build log — the niche-selection, the single-file stack, and two decisions (an SVG gauge and a no-mail-service auth scheme) that were more interesting than the app deserves. I'm not a trucker. I build small free web tools for industries other may find unglamourous or not enticing enough. That honesty matters later. The problem (worth $2–6k/yr to one user) Truckers get a "free time" window at a dock — usually 2 hours. Past that, the broker owes detention pay (~$50–100/hr). Drivers leave an estimated $2,000–6,000/year of it unclaimed, mostly because the math + the paperwork is annoying enough to skip. So the spec wrote itself: In/out times + free hours + rate → dollars owed. Export a dispute-ready PDF they can email the broker. Work on a phone, no login, instant. Validating before writing a line The mistake I almost made: assume the niche is empty because I'd never heard of it. I checked. It is not empty — DockClaim ($49/mo, GPS tracking), Detention Buddy, a couple of $9.99/mo App Store apps, even a free email-gated web calculator or two. That killed my first instinct ("be the only one") but clarified the real wedge: everything is a paid app download or email-gated. The opening was a genuinely free, no-signup, instant web version that also generates the claim PDF. Not "the only detention tool" — the one with the least friction. I'll say more on why I'm careful about that claim at the end. Lesson: validate to find your angle , not just a go/no-go. "Crowded but all friction-heavy" is a fine market. The stack: one HTML file No framework. The whole app is a single self-contained .html — m

SQL-like Queries in FSRS Plugin for Obsidian Spaced repetition in Obsidian usually works as "show all cards with due earlier than today." That's enough for simple cases, but once you have hundreds of notes, you want to filter, sort, and select. My FSRS plugin now has a query language resembling SQL. It turns a markdown block into a live table that updates with every review. ``` fsrs-table SELECT file as "Note", r as "Retrievability", date_format(due, '%d.%m.%Y') as "Due" WHERE r < 0.7 ORDER BY r ASC LIMIT 20 ``` → the table shows the 20 most "forgotten" cards, sorted by retrieval probability. From Simple Settings to an Embedded DB Initially I planned to offer table settings using standard SQL syntax. But pretty quickly the syntax became a real query language, and the implementation itself — an embedded lightweight DB. High-level test coverage in TypeScript made it easy to iterate on functionality located in the WASM module via an AI agent. When faced with dual-language testing (TypeScript + Rust), the artificial intelligence prefers to do the job properly rather than fake it. After implementing the lexer → parser → AST → evaluator pipeline for numeric values, I extended it to strings, added filtering via WHERE, then functions. Extending the syntax or adding a function came down to a single request to the agent — and a feasibility check. What's Inside fsrs-table Supported Features SELECT — choose fields, rename via AS . WHERE — conditions with = , != , < , > , <= , >= , AND , OR . ORDER BY — sort ascending ( ASC ) or descending ( DESC ). LIMIT — cap the number of rows. date_format() — convert the due date to any text format. Available fields: Field (alias) Type Description file string path to the note due date next review date stability (s) number stability in days difficulty (d) number difficulty retrievability (r) number probability of recall (0…1) reps number total number of reviews state string New, Learning, Review, or Relearning elapsed number days since last r

Inspired by a similar project called GenosDB and Cloudflare’s initiative to rebuild Next.js, I decided to rebuild GunDB with a modern coding style, incorporating improvements and addressing shortcomings in the original technology. I used the OpenCode tool with the Big Pickle model to rewrite the project in a new graph database called Garfo (the Portuguese word for “fork”), and I was impressed with the results and its practical applications. In this article, I’ll explain the technology and its improvements over GunDB. Introduction Garfo is a modern, browser-first fork of GUN.js — the decentralized, offline-first graph database. A fork of the original project that keeps the familiar GUN graph API while bringing meaningful improvements to the modern JavaScript ecosystem. Why a Fork? GUN.js is a revolutionary technology — a graph database that syncs in real time, works peer-to-peer, resolves conflicts automatically, and runs in the browser. However, the JavaScript ecosystem has evolved. TypeScript has become the standard, ES modules are the norm, and new transport layers like Nostr have emerged as promising decentralized protocols. Garfo was born to fill these gaps: a GUN rewritten with modern typing, designed with the browser as a first-class citizen, and with native support for the Nostr protocol. Key Features Familiar Graph API If you've used GUN before, you'll feel right at home. Garfo exposes the same chainable API: import Garfo from ' garfo ' ; const db = new Garfo ({ localStorage : true }); db . get ( ' users ' ). get ( ' alice ' ). put ({ name : ' Alice ' , status : ' online ' }); db . get ( ' users ' ). get ( ' alice ' ). on ( profile => { console . log ( ' Update: ' , profile ); }); All the classic methods are there: get() , put() , set() , on() , once() , map() . Optional Nostr Transport This is one of the most exciting additions. Garfo can use Nostr relays as a transport layer, allowing peers to exchange graph messages through public or private relays: const

Criei um gerenciador de downloads desktop em Python e quero feedback da comunidade! O PyFlowDownloader é um app desktop feito com Python + PySide6 que usa yt-dlp para baixar vídeos e áudios de forma assíncrona do youtube. Algumas coisas que ele já faz: Fila de downloads com progresso em tempo real Cancelamento de downloads ativos ou pendentes Suporte a MP4 e MP3, de 144p até 1080p Histórico com exportação para CSV Interface desktop com tema visual via QSS Build para Windows via PyInstaller + pipeline de release no GitHub Actions Está na versão v0.3.0 e ainda tem muito espaço pra crescer. Repositório: https://github.com/Vinny00101/PyFlowDownloader Se você puder **testar e deixar sua opinião nos comentários, ficaria muito grato! Quer saber: O que achou da experiência de uso? Algum bug que encontrou? O que você adicionaria ou melhoraria no projeto? Todo feedback é bem-vindo!

Production incidents almost never break in one place. The alert fires in one tool. The broken deploy is in Netlify. The suspicious change is in GitHub. The stack trace is in Sentry. The human context is in Slack. The runbook is in Notion. The "is this actually paging someone?" answer is in PagerDuty. A normal chatbot can sound helpful in that situation. It can say things like "you should check your recent deployments" and "look for related errors in Sentry." But that is not triage. That is a polished to-do list. I wanted something more useful: an agent that could go get the evidence, connect the dots across sources, show its work, and give an operator-grade answer grounded in real system data. The design constraint from the start was simple: no evidence, no answer. That became ReefWatch , a Coral-powered production triage agent built to investigate instead of improvise. It discovers the tools connected to a workspace at runtime, queries them as evidence, correlates records across systems, and produces a compact answer only when the facts support one. Coral became the backbone because it turns the messiest part of agent tooling into something the model can actually reason about: SQL . What This Guide Builds By the end of this route, you will have a blueprint for an agent that can: discover connected Coral sources at runtime query production systems through read-only SQL correlate evidence across code, deploys, errors, alerts, chats, and runbooks stream every query and row count into an inspectable UI run the same investigation workflow from a CLI when you want a scriptable path generate an incident report only when the evidence supports one stay focused with policy layers instead of a giant prompt blob In one sentence: ReefWatch is a Coral-powered investigation workspace that lets an agent discover connected tools at runtime, query them with read-only SQL, stream the evidence trail, and generate an incident report only when the facts actually support one. Why Coral B

I lost more than 60 days but I made a huge update All OnemanBSD OS is now 64 bits. I also removed all bloat like Rust, Wayland and Qt dependencies from all app ports used in the system. (mpv was changed to gnome-mplayer because of that). New apps included (+ fixed source code of everything): audacity (audio editor) godot (game editor) deadbeef (mp3 player) ted (word processor) Also some bug fixes. Here is the link again: http://bialamusic.com/onemanBSD/ Here are my thoughts: I feel that we as humans are loosing control over technology that was created by humans. This is rising some serious and strange questions. I think we now need tools to power the individual so we can fight back. Not corporations. Not governments. Not organizations. Consider this my bullet in this battle. It is now in your hands so you can be active developers not just passive users.

Over the last few weeks I built a website audit tool and ran it on 200+ small business and service websites — dental practices, plumbing companies, landscapers, law firms, real estate agents. Not Fortune 500 pages optimized by dedicated teams. The sites that actually serve local customers. I expected some issues. I did not expect this. Here's the raw data, the patterns I found, and what you can actually do about it. The Scorecard I grade sites across five dimensions on a 0–100 scale. Here are the averages from 200+ audits: Dimension Average Score Worst Score Speed 56 11 SEO 68 29 Mobile usability 61 18 Accessibility 52 8 Security 70 17 SEO and security tend to be passable (automated checks from Google Search Console and automatic SSL help). Speed and accessibility are consistently neglected — probably because the feedback loop is invisible. A slow or inaccessible site loses visitors silently, and the owner never knows why. Finding #1: 67% of Sites Ship >50% Unused CSS This was the single most surprising data point by far. When a browser loads a page, it downloads every byte of CSS, parses it, builds style rules for every selector, and only then paints. If 60% of those rules never get applied (because they target a contact form behind a click, or a mobile menu at 768px+), the browser still processed them. Worst case: a dental practice shipped 287 KB of CSS. Only 31 KB was used on first paint. That's 256 KB of unnecessary render-blocking weight that delayed First Contentful Paint by roughly 1.4 seconds. The fix: If you're using Tailwind, make sure tree-shaking is enabled. If you're writing vanilla CSS, open DevTools > Coverage tab > Reload. Anything over 40% unused is worth addressing. Most bundlers handle this — you just need to turn it on. Finding #2: Average Image Payload Is 1.8 MB — Way Too High Average image payload across all scanned sites: 1.8 MB per page. Only 34% serve WebP or AVIF (modern formats that cut file size by 30-50%). Only 28% serve responsive sizes

I'm 15 and Built an AI Energy Dashboard with Next.js 15 + Groq Hey Dev.to! 👋 I'm a 15-year-old student developer from South Korea. I just finished my first real production project — FuelScope AI. What is it? An energy market intelligence dashboard that uses Groq's Llama 3.3 70B to summarize real energy news in real time. 🔗 Live Demo: https://fuelscope-ai.vercel.app What it does ⛽ Regional gas price cards 📈 Energy stock tickers (XOM, CVX, SHEL) 🤖 AI-summarized energy news (Llama 3.3 70B via Groq) 🗺️ Interactive Mapbox station map 📍 GPS nearest station finder 🎨 Apple-inspired clean design Tech Stack Next.js 15 + TypeScript Tailwind CSS Groq API (Llama 3.3 70B) — FREE tier GNews API — FREE tier Mapbox GL JS Vercel deployment What I learned This was my first time building something with: Real API integrations AI summarization pipeline Production deployment on Vercel Apple design system principles Honestly learned more in 4 days building this than months of tutorials. Honest disclosure Gas prices and stock data are mock values — the README includes guides for swapping in real APIs (EIA, Alpha Vantage, etc.). The AI news summaries are 100% live though. Template I'm selling the template for $19 on Gumroad if anyone wants to build on top of it: 👉 https://LZF01.gumroad.com/l/djzoaj Would love any feedback from the community! 🙏 Built with Next.js 15, Groq, GNews, Mapbox

Meet Halimun Proxy a high-performance, ultra-low latency proxy tunnel system built from the ground up in Rust. Why Rust? By leveraging Rust , Halimun achieves extreme efficiency. Using the Axum web framework and Tokio for non-blocking asynchronous I/O, it manages to maintain a tiny footprint—running on as little as ~15MB of RAM . It’s designed to be fast, memory-safe, and incredibly stable under load. Core Security Features Halimun isn't just a proxy; it’s a security layer. It enforces strict request validation to ensure your internal services are never exposed to malicious actors: AES-256-CBC Encryption: End-to-end payload masking. Even if your traffic is intercepted, the actual API endpoint and data remain indecipherable. HMAC-SHA256 Integrity: Validates that data hasn't been tampered with in transit. Replay Attack Prevention: Uses Nonce and timestamp verification in-memory (via DashMap ) to reject duplicate spoofed requests. SSRF Protection: Built-in mechanisms to prevent attackers from targeting your internal network infrastructure (e.g., 127.0.0.1 ). Camouflage Routing: It hides your actual API structure behind random, dummy URL segments, making traffic profiling by WAFs or human analysts nearly impossible. Quick Start (Docker) Halimun is "Docker-ready," making it easy to drop into any existing infrastructure. 1. Configuration First, generate your encryption keys using the built-in generator: # Generate keys and save to .env docker build -t halimun-proxy . docker run --rm halimun-proxy ./halimun-proxy --keygen --format = env > .env 2. Deployment Configure your config.yaml to map your backend services, then launch your cluster: docker-compose up -d Your production proxy is now live, listening securely on port 80 while your backend services remain completely secluded within a private Docker network. Under the Hood: Request Lifecycle Halimun uses an encrypted tunnel approach. A typical request follows this structure: POST /proxy/1/SEGMENT1/SEGMENT2/SEGMENT3/SEGMEN

I recently launched LuaPlay, a free browser-based Lua editor. No setup, no install — just open the site and write Lua. Why I built it: Every time I wanted to test a quick Lua snippet, I had to either open a local environment or use tools that weren't built for Lua specifically. So I built my own. What it does: Run Lua scripts directly in the browser Clean, minimal editor interface Free to use Would love feedback from the dev community. What features would make you actually use it day-to-day? 👉 https://luaplay.online

I Built a Local AI Agent That Thinks Like a Brain, Not a Database Most AI agents today are sophisticated autocomplete engines. Ask them something, they answer. Ask again in a new conversation, they start from zero. The context window is the only memory they have. Serenity is different. It's a fully local AI agent that encodes experiences the way biological brains do — semantically clustered, causally structured, and self-organizing. No cloud. No API calls to a vector database. No data leaves your machine. Ever. The Core Problem with Current AI Memory The standard approach to AI memory is essentially a hack: you stuff embeddings into a vector DB, do nearest-neighbor retrieval, and dump the results into the prompt. It sort of works. But it's not how brains work. Your brain doesn't search for memories. When one fires, related ones light up automatically. Serenity's architecture — called S.E.R.A (Semantic Experience Reasoning Agent) — tries to bridge that gap. Here's the key difference: Traditional Approach Serenity Vector search on embeddings Semantic node activation Prompt-injected context Persistent working memory One-shot retrieval Emergent recall via association Static embeddings Pruned & crystallized over time How It Works: The Neural Node Network At the core is the Neural Node Network (NNN) . Instead of storing facts in isolation, Serenity encodes experiences in causal format: ACTION → BEFORE → OUTCOME → AFTER When she learns something, she doesn't file it in a folder. She finds where it semantically belongs in a web of related concepts. Similar things cluster together — the same way neurons that fire together wire together. Then the abstraction layer kicks in. Three or more related concepts crystallize into a higher-order node: the thing they all have in common that none of them says directly. Those nodes bundle into pathways. Those pathways grow into domains. She also has inhibitors and pruning — weak connections get cut so strong ones sharpen. Her knowledge ge

I use "what is my IP" sites maybe once a month. Every time I end up on something covered in ads, calling three different tracking APIs, and showing me results I don't fully understand. So I spent a weekend building whatsmy.fyi. The thing I didn't expect: you don't need an IP geolocation API at all if you're on Cloudflare Workers. Every request comes with a cf object that already has your city, country, ISP, TLS version, HTTP protocol, and RTT. Free. Zero latency. The part I enjoyed most was the WebRTC leak test. It checks whether your browser is exposing your real IP through RTCPeerConnection even when you're on a VPN. I ran it on my own setup. It was leaking. Zero logs. Zero storage. Just your data, shown to you. https://whatsmy.fyi

A while ago I tried to build a local coding assistant. I downloaded Qwen3, fired it up on my MacBook with 16GB of RAM, and within a day realized the output quality was nowhere close to Claude or GPT-5. The model could fit . It just couldn't compete . So I changed the question. If I can't make the model smarter on my hardware, can I make what I feed it smarter? Where the tokens actually go I started watching where my Claude / Cursor / Copilot sessions actually spent their tokens. The surprise: most of it wasn't reasoning. It was lookup . Every fresh chat about my company's database re-discovered the same things: What does status = 3 mean? (cancelled) How does orders join to users ? ( orders.user_id → users.id ) What's that cryptic JobStatus enum? (a dozen integer codes nobody remembers) The model figured it out, the session ended, and tomorrow it figured it out again . Same tokens, same latency, every single time. The expensive part of working with an AI wasn't the thinking — it was re-teaching it things it had already learned yesterday. There's a lot of attention right now on trimming AI output tokens (talk like a caveman, strip the pleasantries, etc.). But in my workflow the bigger leak was on the input side: paying full token cost every session to re-establish context that never changed. "Memory" isn't a feature, it's an architecture question AI clients are starting to bolt on "memory" features. But they're proprietary, opaque, and locked to one tool. Claude's memory doesn't help Cursor. Cursor's doesn't help Copilot. You can't inspect it, you can't share it with a teammate, and you can't diff it. What I actually wanted was an explicit, inspectable, shareable context layer that any AI client could read deterministically — same answer every time, same file my team could hand off. I picked the highest re-learn cost in my world to start with: SQL databases. Enter amnesic amnesic is an open-source MCP server that gives any AI client persistent semantic memory of your

I used to live in VS Code with GitLens pinned — the branch graph, heat-mapped blame, the lens annotations. That was my git workflow. Then 2026 happened. With Cursor, Claude Code, and Codex doing the actual editing, the editor itself became optional. The only thing dragging me back was GitLens. That felt wasteful — booting an entire IDE just to peek at commit history. The agent runs the git commands now; I only need to sanity-check the result, occasionally, when something looks off. So I built gitwink — the smallest possible tool for that loop. A tray icon that expands into a glance, hands the commit off as AI context, and gets out of the way. Read-only by design. It cannot commit, push, merge, or modify anything. If I need git surgery, I tell the agent. The 0.5-second confirm loop agent commits → tray click → inline expand → "Copy as AI context" → paste into Claude/Codex/Cursor → "did the agent do this right?" No window switching. No IDE boot. The whole loop fits inside a glance. What's in it Tray-resident (Windows tray / macOS menu bar) — click to toggle, global hotkey Ctrl+Shift+G to summon from anywhere. Right-click the tray icon for Reset position / Open settings file / Quit. First-run discovery that walks your usual code dirs ( source , Documents , Projects , Code , Dev , repos , Desktop , every non-system drive on Windows; ~/Projects , ~/Code , ~/Developer on macOS) and caches the result in SQLite. No "add repo" friction. Unified commit timeline across all repos, with chips above for filtering by Repo (search + pinning), Time range (24h / 3d / 7d / 30d / All), and Authors (multi-select with counts). Per-row markers — ● commit · ◆ merge · ★ tagged — and branch label badges when a commit isn't on the currently checked-out branch. Single-repo DAG view — pick a repo and the panel switches to a per-branch graph with a custom SVG lane drawer (eight-colour palette, hashed from branch name; main / master / develop kept neutral). Inline expand on click — commit body +