标签：#showdev

This project presents an offline voice agent that uses Indonesian law data from the Pasal ID API and is optimized for the Indonesian language. It is capable of understanding spoken Indonesian, generating responses in Indonesian, and speaking back in Indonesian without requiring cloud APIs. The system combines Whisper-based speech recognition, Ollama-hosted LLMs, and local text-to-speech models to provide a privacy-preserving conversational AI experience. You can access the project repository here: PasalVA . Usually, when using voice assistant applications, we need to rely on cloud-based services, which creates dependence on third-party providers. An internet connection becomes mandatory, which impacts usability in environments with limited or unreliable network access. In addition, cloud-based solutions require operational costs because requests must be sent to third-party servers. To address these challenges, this project aims to develop a fully local voice agent that is capable of functioning as a voice assistant by eliminating external service dependencies while supporting the Indonesian language. System Architecture The application flow follows a voice assistant architecture with additional Retrieval-Augmented Generation (RAG) capabilities to retrieve relevant Indonesian laws. User │ ├── Text Query │ │ │ ▼ │ Text Input │ └── Voice Query │ ▼ Microphone │ ▼ Speech-to-Text │ ▼ Text Processing │ ▼ Retrieve Related Laws │ ▼ LLM (Ollama) │ ▼ Response Text │ ├── Display in UI │ ▼ Text-to-Speech │ ▼ Speaker Output The application allows users to either type their query or use a microphone to ask a question. For voice input, the audio is first converted into text using a Speech-to-Text (STT) model. The resulting text, along with directly typed queries, is then processed to remove noise and normalize the input. After preprocessing, the query is converted into embeddings and used to retrieve relevant Indonesian laws from the local knowledge base. The retrieved legal contex

A few months ago I was trying to prepare for a cloud certification exam. I went looking for practice questions - good ones. Not just answer lists, but questions that actually trained the reasoning the exam tests. I found some scattered GitHub repos, a few YouTube playlists, sites with outdated question dumps. Nothing that felt structured. Nothing that explained why an answer was right, not just what it was. So I started building my own study tool. Mock questions, practice sets, AI-generated explanations. The kind of thing I wished existed. Six weeks later that became ArchReady - a certification prep platform for AWS, GCP, and PSM1. It's live now. What it does Practice questions across AWS (CCP, SAA, DVA, SAP), GCP ACE, and PSM1 Explanations for wrong answers - walks through the reasoning, not just the correct option AI-powered explanations coming soon Claude (Anthropic) Confidence tracking - shows which topics you're weak on Free to practice, no signup required. Pro unlocks full history and tracking. The stack Frontend: Next.js 14 (App Router) Backend: FastAPI (Python) AI: Claude (Anthropic) - explanations launching soon Payments: Dodo Hosting: Vercel (web) + Railway (API) Nothing exotic. I kept it boring on purpose - solo founder, 2-5 hrs/week, I can't afford interesting infrastructure problems. What I actually learned Ship before it feels ready. I had a list of 12 features I thought were "required for launch." I launched with 4. Nobody noticed the missing 8. Questions sourced from open-source + AI is good enough to start. Questions come from curated GitHub repos and AI-generated content built around official exam frameworks. That's enough to be useful. Perfection is a later problem. The hardest part isn't building - it's the first 10 users. The product exists. Getting people to try it is the actual work now. Where it is today Live at archready.io . Early stage. Still building. If you're prepping for AWS, GCP, or PSM1 - try it free, no account needed. Honest feedba

I Built a GDPR Compliance Scanner Using the Claude API - Here's How It Works A few months ago I noticed something that kept bugging me. I was building and handing off websites for clients and every single time, GDPR compliance was either an afterthought or a panic right before launch. Privacy policies copied from templates, cookie banners slapped on at the last minute, no one really sure if the contact form was actually compliant. The bigger problem: there was no quick, affordable way to check . Enterprise compliance tools cost hundreds per month. Legal consultants cost more. Most small businesses just crossed their fingers. So I built ClearlyCompliant - an automated GDPR compliance scanner that analyses a website and delivers a detailed PDF report for a one-off fee. No subscription, no jargon, just a clear picture of where a site stands. Here's how it actually works under the hood. The Stack Django (Python) - backend and web app BeautifulSoup + requests - crawling and HTML parsing Python threading - async scanning without the overhead of Celery/Redis Anthropic Claude API (Haiku) - AI-powered policy analysis ReportLab - PDF report generation Stripe - payments IONOS SMTP - email delivery Gunicorn + Nginx on an IONOS VPS The Scanning Pipeline When a user submits a domain and completes payment, the scan kicks off immediately. Rather than making them wait on a loading screen, the scan runs asynchronously in a background thread and the report gets emailed when it's done. I deliberately avoided Celery and Redis here. For the scale I needed, Python's built-in threading module was more than sufficient and kept the infrastructure simple. One less thing to maintain, one less thing to break. import threading def run_scan_async ( domain , order_id , customer_email ): thread = threading . Thread ( target = run_full_scan , args = ( domain , order_id , customer_email ) ) thread . daemon = True thread . start () The scan itself runs 23 individual GDPR checks across several categori

I built ResizeKB — a free image and PDF resizer built specifically for Indian users. 25+ tools. Zero server uploads. Pure HTML, CSS, JavaScript. Here's how and why. The Problem Every Indian applying for government jobs, exams, or bank accounts hits the same wall — portals with strict KB limits rejecting documents. UPSC wants photo under 300KB. SSC wants under 50KB. Banks need Aadhaar PDF under 500KB. Every portal is different. Every rejection wastes someone's time and opportunity. Most people have no idea how to resize to an exact KB. They either give up or use random tools that upload their Aadhaar and PAN card to unknown servers. I built a tool that solves this in one click — with zero server upload. The Tech Stack No framework. No backend. No database. Canvas API for image processing pdf-lib for PDF compression Vanilla JavaScript only Cloudflare Pages for hosting — free, global CDN, auto deploys from GitHub Total infrastructure cost: ₹1,162 per year for the domain. Everything else free. Image Compression — The Binary Search Algorithm The core challenge is compressing to an exact KB target without over-compressing. Most tools use a fixed quality setting like 60% which destroys image quality. The right approach is binary search on JPEG quality: javascriptasync function compressToTargetSize(file, targetKB) { const targetBytes = targetKB * 1024; let low = 0.1; let high = 1.0; let result = null; const img = await loadImage(file); const canvas = document.createElement('canvas'); canvas.width = img.width; canvas.height = img.height; const ctx = canvas.getContext('2d'); ctx.drawImage(img, 0, 0); while (high - low > 0.01) { const mid = (low + high) / 2; const blob = await canvasToBlob(canvas, 'image/jpeg', mid); if (blob.size <= targetBytes) { result = blob; low = mid; } else { high = mid; } } return result; } This finds the highest quality setting that still hits your target KB. Result is the sharpest possible image at that file size — never over-compressed. PDF Compress

The main difference between a developer and an engineer is not just the code they write. It's how they think about building a system. How they optimize. How they use resources. I learned this from a real project. I had to read 10,000 JSON requests and write them into a file. Simple enough. I wrote the program the way I always did the developer way. Read all 10,000 requests, store everything in memory, then write to the file. Done. When I tested it, my memory usage was much higher than normal. Way higher than it should have been. The developer in me would have just moved on. It works, right? But something made me stop and ask why is this consuming so much memory? I dug into it. And I found the problem. What I was doing was basically doubling my memory usage without realizing it. First, I was loading all 10,000 records into memory to store the data. Then, I was holding all of it again in memory while writing to the file. Two copies of the same data sitting in memory at the same time. That's the thing about this approach it's not reliable when you're dealing with a large number of requests. It doesn't scale. It just quietly eats your resources. That's when I found streams. The idea behind streaming is simple but powerful. Instead of loading everything at once, you break the data into small chunks. At any given moment, only one chunk lives in memory. You read it, transform it, write it and move on to the next one. The transform step is the interesting part. It's not just about moving data from one place to another. Transform lets you validate each chunk, check if the structure is correct, clean it if needed before it ever reaches the file. So you're not just being efficient with memory, you're also processing your data with more control. And because you're always working on one small piece at a time, the memory usage stays low and consistent no matter if you're processing 100 requests or 100,000. That one question am I using my resources in a reliable way? is what pushe

Two weeks ago I shared a collection of 6 financial calculators. The response was incredible, so I kept building. Today, fi-calc.com has 25 completely free calculators covering every major personal finance need: 🏠 Housing • Mortgage Calculator (full PITI + amortization schedule + pie chart) • Rent vs Buy Calculator • House Affordability Calculator • Refinance Calculator 💰 Investing & Retirement • Compound Interest Calculator • Investment Return Calculator • Future Value & Present Value Calculators • ROI Calculator • Retirement Savings Calculator • 401(k) Calculator • FIRE Calculator (Financial Independence) 💳 Debt & Loans • Loan Comparison Calculator • Auto Loan Calculator • Student Loan Calculator • Credit Card Payoff Calculator • Debt Payoff Calculator (Avalanche method) 📊 Everyday Finance • Budget Planner (50/30/20 rule) • Savings Goal Calculator • Inflation Calculator • Salary & Take-Home Pay Calculator • Net Worth Calculator • Currency Converter (15+ currencies) • CD Calculator • Sales Tax Calculator ✨ Tech Stack • Pure vanilla HTML/CSS/JS — no frameworks • Chart.js for animated interactive charts • Responsive design (mobile-friendly) • All calculations run client-side in your browser • No data collection, no accounts, no cookies 🔗 Give it a try: fi-calc.com The entire site is free and open. I built it because I was tired of calculator sites with paywalls, signup walls, and bloated ad experiences. Would love feedback from the community! What other calculators should I build next?

Hey DEV community! 👋 I just completely rebuilt and launched Mailfo v2.0 , an privacy-focused temporary disposable email app for Android[cite: 1, 2]. The first version got the job done, but it lacked the fluid user experience, offline reliability, and sleek UI that modern mobile apps need. I decided to tear it down and rewrite it from scratch using Jetpack Compose , Room DB , and modern Android architecture[cite: 1]. Here is a breakdown of what went into the rebuild, why privacy tools like this are essential, and what's new[cite: 1]. 🛡️ Why Use a Temporary Disposable Email? We’ve all been there: you want to download a single source-code snippet, test a new app, or sign up for a one-time service, but you don't want your primary inbox flooded with endless marketing spam[cite: 1]. A disposable email address acts as your personal buffer[cite: 1]. It protects your personal data, prevents tracker exposure, and keeps your real inbox clean[cite: 1]. ⚠️ Pro-tip: Mailfo is designed strictly for low-risk temporary email needs[cite: 1]. Do not use disposable email addresses for banking, legal accounts, or primary account recoveries[cite: 1]! 🛠️ The Tech Stack & Architecture Upgrades Moving from version 1.0 to 2.0 meant migrating away from legacy views to a fully declarative UI workflow[cite: 1, 2]. UI/UX Architecture: Built entirely with Jetpack Compose for smooth performance, a modern look, and native Light, Dark, and System theme switching[cite: 1]. Navigation: Implemented an intuitive bottom navigation system dividing the app into distinct Home, Inbox, and Profile tabs[cite: 1]. Caching & Offline Stability: Integrated a local Room SQLite database to cache inbox summaries and message data[cite: 1]. This guarantees instantaneous screen transitions without annoying network loading spinners[cite: 1]. ✨ Key Features in Mailfo v2.0 Custom & Random Email Generator: Instantly spin up a completely randomized address or build a custom email username using multiple searchable domains[ci

​We just deployed a major update to our SQL Server web sandbox, moving from an individual tool to a collaborative environment: ​✅ Group Rooms (Beta): Create private rooms using security tokens to chat and write code together in real time. ✅ Simulated Linked Servers (Beta): Connect with your friends' sandboxes to run cross-queries strictly in read-only mode to preserve performance. ✅ Gamification & XP: Earn experience points and unlock technical badges as you run queries or build database schemas. ✅ Social Layer: Manage your friends list and customize your public developer profile to showcase your achievements. ​Currently, all features are completely free to use during this phase of the platform. Try it out with your colleagues at tsqlsandbox.online and leave your feedback below!

Here's the maths most calculators get wrong Most freelance rate calculators are wrong. Not buggy — conceptually wrong. They take your income goal, divide by hours, and hand you a number that will quietly lose you money all year. I got tired of explaining the correct calculation to freelancer friends, so I built a tool that does it properly. Here's the logic behind it, and a bit about how I built it. The flawed formula The typical calculator does this: hourly_rate = annual_income_goal / annual_hours_worked So if you want $80,000 and work 2,080 hours a year (40 × 52), it tells you to charge ~$38/hr. This is wrong in three separate ways. Fix 1: Tax is not optional Your income goal is a net number — what you want to keep. But you're taxed on gross. So the first correction is grossing up: const grossIncome = netTarget / ( 1 - taxRate ); // $80,000 / (1 - 0.28) = $111,111 That's already a $31,000 gap the naive formula ignores. Fix 2: You don't bill every hour you work This is the big one. Freelancers bill roughly 55–65% of their working hours. The rest is admin, proposals, invoicing, sales calls, and learning. const totalHours = weeksWorked * hoursPerWeek ; // 46 * 40 = 1840 const billableHours = totalHours * billableRatio ; // 1840 * 0.6 = 1104 So your real billable capacity isn't 2,080 hours. It's closer to 1,104. Pricing on the wrong denominator is how people end up working 50-hour weeks and still missing their income target. Fix 3: Business expenses come out of gross Software, hardware, insurance, courses — all real costs that need covering before you pay yourself: const totalNeeded = grossIncome + annualExpenses ; The corrected formula Putting it together: function minimumRate ({ netTarget , taxRate , expenses , weeks , hoursPerWeek , billableRatio }) { const gross = netTarget / ( 1 - taxRate ); const totalNeeded = gross + expenses ; const billableHours = weeks * hoursPerWeek * billableRatio ; return totalNeeded / billableHours ; } minimumRate ({ netTarget : 80000 ,

A few months back I got frustrated. I needed to calculate something — nothing crazy, just a loan payment — and every site I landed on either wanted me to sign up, showed ads on every input, or was in English only (not helpful when sharing with family abroad). So I built Calculora . It's a free calculator site. 150+ tools, 13 languages, zero data collection. Everything runs in your browser — nothing gets sent anywhere. Why 13 languages? Because most people on the internet don't speak English as a first language. I wanted it to actually work for them — not just have a translated homepage, but real localized URLs, right-to-left layout for Arabic, the whole thing. Getting that right in Next.js took more time than I expected. Each tool has a different slug per language, so the routing has to map hundreds of combinations correctly. Totally worth it though. The math rendering For tools like the equation solver and statistics calculator, I wanted the formulas to look like real math — not just text. I used KaTeX for this. It's fast, lightweight, and renders LaTeX properly in the browser. The step-by-step solutions actually show the working — discriminant, roots, the full process — rendered cleanly. Some tools I'm proud of Equation Solver — linear and quadratic, with full steps shown Statistics Calculator — mean, median, mode, IQR, std dev, exportable FIRE Calculator — retirement planning done simply Debt Snowball/Avalanche — side-by-side payoff comparison What's next More tools, better mobile experience, and filling in gaps across the language versions. If you try it, I'd genuinely love feedback — especially on anything that feels off or missing. calculora.net

Most side projects start with a simple frustration. Mine started with a banking app. One of my banks had a feature I really liked. It automatically categorized transactions and showed spending breakdowns in graphs and charts. For the first time, I could easily see how much I spent on restaurants, groceries, transport, subscriptions, and other categories. The problem was that only one of my banks offered this feature. Like many people, I use multiple bank accounts, credit cards, and savings accounts. Two of my other banks provided little more than a long list of transactions. If I wanted a complete picture of my finances, I had to switch between apps and manually piece everything together. As a software engineer, my first instinct was obvious: "Why don't I just build this myself?" That idea eventually became MyVault . The Original Goal The first version of the project was surprisingly simple. I wanted users to: Upload bank statements Extract transaction data Automatically categorize spending View useful charts and reports The goal wasn't budgeting. It wasn't investment tracking. It wasn't accounting. I simply wanted a single place where I could see spending across all of my bank accounts. Once I started building, however, I realized there was a much more interesting opportunity. If all transaction data was already extracted and structured, why not allow users to ask questions about their finances? Instead of searching through transactions manually, users could simply ask: How much did I spend on restaurants last year? What subscriptions am I paying for? Which categories increased the most this month? How much did I spend while traveling? That's when MyVault started evolving from a reporting tool into an AI-powered financial assistant. Building as a Solo Developer One of the biggest challenges wasn't technology. It was building everything alone. When you're working on a side project, you don't just write code. You become responsible for everything: Product decisions B

The Problem If you've ever audited your Windows network traffic during a boot-up sequence, you know the truth: there's a "blind spot." Between the moment your network drivers initialize and your VPN/WireGuard tunnel actually establishes, your traffic is leaking. Many third-party solutions exist, but they are often bloated, use proprietary binaries, or act as black boxes. I wanted something transparent, native, and bulletproof. The Solution: WG-KillSwitch I developed a pure PowerShell-based kill switch architecture. It doesn't rely on third-party libraries—it uses native Windows system components to enforce security. Key Architectural Features: Zero-Trust Firewall Matrix: Hardens the system by blocking all outbound traffic by default, allowing only authenticated tunnel traffic. WMI Persistent Watchdog: Unlike standard scripts that can be killed via Task Manager, this project uses WMI Event Subscriptions. If the watchdog process is terminated, Windows itself immediately respawns it. Resilience: Survives hard reboots, modem resets, and Windows service cycling. Resilience & Leak Testing I've put this through a gauntlet of tests: Forced Reboots: Zero leaks detected during driver load. Process Termination: The WMI engine restores the protection in milliseconds. Dynamic Network Resets: The firewall matrix remains active regardless of adapter status. Let's Collaborate This is open source, transparent, and built for the community. I'm looking for security audits and feedback. Check out the source code, open an issue, or submit a PR: https://github.com/ryderlacin-pixel/Windows-WireGuard-KillSwitch

Hi everyone, As a Full-Stack and Cloud engineer, I’m used to automating everything I can. Whether I'm managing my 28+ container Kubernetes homelab on Proxmox or writing deployment scripts, I absolutely hate doing the same manual task twice. But a few months ago, when I was hunting for a new role, I found myself doing exactly that: manually tweaking my resume for every single job, copy-pasting into black-box ATS portals, and tracking it all in a chaotic spreadsheet. It was completely draining. So, I took a break from the applications and built a tool to solve my own problem. It’s called OneApply. It started as a small browser extension to check ATS keywords, but it quickly snowballed into a complete workspace. Here is what the stack handles now: Resume Tailoring: Automatically adjusts your resume to fit specific job descriptions. ATS Keyword Scoring: Checks your overlap with the job description so you know you'll actually pass the automated filters. Cover Letter Generation: Drafts contextual cover letters based on the role and your specific engineering experience. Pipeline Tracking: Manages all your applications natively so you can finally ditch the spreadsheets. Building this and using it to automate the worst parts of the daily grind actually helped me land my current SRE role. Since it worked for me, I decided to polish it up and release it for other devs who are currently stuck in the application trenches. We all know the tech market is tough right now, and any edge helps. I would love for this community to try it out and roast the UX, the workflow, or the core features. Check it out here: https://www.oneapply.app I am more than happy to hand out some premium access codes to anyone here who is actively applying and wants to test drive the full feature set. Just drop a comment below!

Hey everyone! Our team and I (acting as a junior backend) recently finished rebuilding GlobeVM (an enterprise Cloud, IT, and Cybersecurity provider) from a traditional monolithic WordPress site into a Headless architecture. I wanted to share our entire journey, our tech stack, the massive headaches we faced, and the solutions we engineered. If you are planning a Headless WP build soon, grab a this might save you weeks of debugging! The Tech Stack Frontend: Next.js (App Router), React, deployed on Vercel. Backend: WordPress hosted on Cloudways (Purely as a headless CMS). Data Structure: Advanced Custom Fields (ACF Pro) + Custom Post Type UI (CPT UI). SEO: Yoast SEO Premium (via REST API). Caching: Vercel Edge Cache (ISR) + Redis Object Cache on Cloudways. During the development and deployment of this website we faced several issues containing the frontend stack itself and traditional features of WordPress. I tried my best to save them all and show them all up here for everyone so that we can discuss on every section of it, maybe we could reach to even something more special :) Challenge 1: The API Was a Mess ("BFF" Architecture) When we first started, we were using the default WordPress REST API. Our Next.js frontend was making 8 different fetch() calls just to build the Blog Homepage (fetching posts, authors, categories, tags, ACF fields, etc.). We were also using messy URLs like ?_fields=id,title,acf&_embed. The Solution: We built a Backend-For-Frontend (BFF). Instead of Next.js doing the heavy lifting, we wrote a custom PHP plugin in WordPress. We created a single master endpoint (/wp-json/gvm/v1/blog-home). WordPress ran all the complex database queries, bundled the Tags, Hero Article, and Categories into one beautiful JSON array, and cached it in RAM using Transients & Redis. Only one of WordPress default api was used for our categories. Result: Next.js made one fetch call. The page loads instantly.' Challenge 2: Handling Vector Icons & ACF Our design heavily re

I built AIPDFKit because I kept running into the same friction: needing to do something simple with a PDF -- redact some sensitive info, pull out a table, or convert a document to Markdown -- and every tool either required an account, put the good stuff behind a paywall, or made me wonder what was happening to my files afterward. PDFKit is my answer to that. PDFKit -- Free AI-Powered PDF Tools PDFKit is a free, browser-based PDF utility suite powered by AI, built for developers and technical professionals who need fast, reliable document processing without the friction of paid plans or mandatory accounts. Whether you're parsing data out of PDFs, sanitizing sensitive information, or converting documents into developer-friendly formats, PDFKit gets the job done in seconds. What it does AI-assisted PII redaction -- automatically detect and mask emails, phone numbers, names, and more Table extraction to Excel -- pull structured data out of PDFs without copying and pasting PDF to Markdown conversion -- especially useful for feeding document content into LLMs or RAG pipelines These aren't just format converters. The AI layer means the output is clean, structured, and actually ready to use. Privacy first No account creation required. PDFKit stores no user data and automatically deletes all uploaded files after one hour. For developers handling client documents or sensitive data pipelines, this is a meaningful differentiator over SaaS tools that retain files indefinitely. Who it's for Developers preprocessing PDFs before feeding them into RAG pipelines Anyone automating document workflows People who need to quickly extract structured data without spinning up a Python script Anyone dealing with sensitive documents who can't afford to have files sitting on someone else's servers It's the kind of utility you bookmark and reach for constantly. Built to be fast, free, and frictionless. Check it out: https://www.aipdfkit.com/ Would love to hear what features you'd find most usefu

We are exploring an experimental blockchain mechanism called "Proof of Weather" In the world of blockchain, various methods are used to achieve network consensus. The most well-known is Bitcoin’s Proof of Work (PoW). While PoW is an excellent mechanism, it has one major drawback. It consumes an enormous amount of electricity. At one point, I found myself wondering: Does blockchain really require such vast computational resources? Isn’t there something else that’s needed? This led to the creation of Dawn, the experimental cryptocurrency project I am developing, and an experimental blockchain mechanism called Proof of Weather. In this article, I will discuss: Why I decided to use weather How Proof of Weather works Security considerations Implementation in Rust How Does Proof of Work Work? Proof of Work is often explained as a mechanism where computers compete against each other in computational tasks. However, one important property of PoW is that it produces outcomes that are difficult to predict in advance. Miners repeatedly perform massive amounts of hash calculations, and only those who happen to meet the conditions can generate a block. This unpredictability plays a role in determining who can produce the next block. However, this process consumes enormous amounts of electricity worldwide. So I wondered: Aren’t there already phenomena in nature that are difficult to predict? Why Weather? Proof of Weather utilizes weather data as that unpredictable element. Of course, weather forecasts exist. However, Temperatures several days in the future Atmospheric pressure at specific locations Precipitation Wind speed and other factors cannot be predicted with absolute certainty. In particular, when combining observations from multiple locations, it becomes even more difficult to accurately calculate future values in advance. In other words, meteorological observations have the potential to be used as A real-world information source where future values cannot be fully predic

This is a submission for the GitHub Finish-Up-A-Thon Challenge Note: AI is currently a Hot Topic in...

Just wanted to share my journey after 3.5 years of building a live web analytics tool from scratch, and without AI: WireBoard.io As a web publisher for the last 15 years, I used UA (before GA4) and then Chartbeat. I always loved real-time. At the beginning of the internet I spent my time on IRC, which was great and a huge change from newsgroups and forums. A few years later, Chartbeat was changing its customer base and focusing on big news publishers, and my workflow was about to change with it. I loved being able to watch my traffic live and spot anything unusual, day by day, compared to the same day the previous week. So I decided to replace it with my own product, but with the things their tool was missing. I spent about 8 months thinking it through and sketching different architectures to handle the load and the logic of the data processing pipeline. Then I learned to code in Go (which was surprisingly easy) and built an MVP. After some iterations, I worked on the frontend (Laravel + React) and kept improving the product based on user feedback. The features I couldn't find anywhere else: Truly real-time data via streaming instead of polling. Merging data from different websites into one chart, so I can see at a glance whether traffic is unusual "today" compared to last week. A flexible dashboard, arranged like widgets on a phone. I mostly worked on this quietly and didn't talk about it much on social media or anywhere else, since I'm a dev and not a marketer. This is my biggest project, and I've enjoyed the long journey. All of this happened before the AI era, which turned out to be good timing: I can work on the codebase knowing exactly what does what and where. Over the last 6 months I've experimented with using Claude on some parts of the project (only the frontend), but in limited areas: Performance improvements (useMemo, etc.) Security reviews (not strictly needed, but reassuring when it confirms what I expected) CMS (blog section) The tech stack: Data proc

TL;DR I built AutoMaintainer , a multi-agent AI system that transforms GitHub issues into production-ready pull requests during the Qwen Cloud AI Hackathon. It coordinates specialized agents (Issue Analyst, Developer, QA, Security, Documentation, Reviewer) to solve problems like a real engineering team—all while keeping humans in control. Here's what I learned. The Problem Open-source maintainers face a brutal reality: 📚 Overwhelming issue backlogs 🔄 Repetitive bug fixes and documentation gaps ⏱️ Code review bottlenecks 😴 Burnout from handling everything solo Existing AI tools help write code, but they don't orchestrate the entire workflow: planning, development, testing, security review, documentation, and human approval. What if we could build an AI engineering team that collaborates like real developers? The Solution: AutoMaintainer AutoMaintainer is a multi-agent orchestration system that mirrors a real software company: Issue Analyst – Reads GitHub issues, extracts requirements, assesses severity Architect – Analyzes repo structure, designs the implementation approach Developer – Writes code, updates files, creates new modules QA Tester – Generates tests, validates fixes, checks edge cases Security Agent – Scans for vulnerabilities, prevents dangerous patterns Documentation – Updates changelogs, PR summaries, release notes Reviewer – Scores code quality, recommends improvements Human Approval Gateway – Final human review before merge The result? A pull request that's analyzed, built, tested, secured, documented, and reviewed—all before a human ever sees it. Tech Stack Frontend Next.js – React framework for the dashboard UI Tailwind CSS – Rapid, utility-first styling TypeScript – Type safety for the frontend layer Backend FastAPI (Python) – Lightweight, async-first API Qwen-compatible LLM API – AI model integration for all agents SQLite + Async (aiosqlite) – Persistent pipeline and memory storage Redis-ready architecture – Prepared for distributed queuing Integr

It is time to put my proposition made in my previous blog post to the test. Is it possible to spec an application for execution by an agent without encoding it in source? Let's find out. One type of application every knowledge worker is familiar with is task management. Every task has a lifecycle status, dependencies on other tasks, and a history of progress. Let's give agents their own. TaskTrack is a simple but non-trivial task management system variant implemented as a Specify spec. It goes beyond checkbox-based to-do lists that agents sometimes use internally and mimics the key system features listed above. TaskTrack defines two procedures: a "Plan Authoring Run" to create an interconnected set of tasks from requirements and a "Plan Execution Run" to advance a previously authored plan toward completion. One execution run might not always be enough to achieve completion, because TaskTrack allows requesting human feedback and incorporating it during the next execution run. Furthermore, every execution run is divided into "Task Processing Run" sub-procedures to allow for advanced agent context management. TaskTrack implements all of this in less than 300 lines of text. If the implementation used source code, then, depending on the programming language, this would be enough space to implement only the required file I/O operations (TaskTrack uses files for simplicity, not a database). Natural language can easily become quite bloated, but a stringent, scientific writing style and extensive use of what the Specify standard offers can effectively counter that. The official test is, how could it be any other way, the implementation of yet another uninspired Breakout clone. The requirements, the completed TaskTrack plan, and the deliverable are contained in the repository. If you want to run the test yourself, the included README file contains the necessary information, including the launch prompts for both the authoring agent and the execution agent. Please note how both