标签：#devchallenge

This is a submission for the Hermes Agent Challenge : Build With Hermes Agent What I Built Real brewing knowledge lives in human experience — in roaster guides, in community notes, in what a barista learned from last Tuesday's pour. It doesn't accumulate anywhere. Every brew is forgotten. Ask any AI and you get statistical averages: 93°C, 1:16 ratio, four minutes. Technically defensible. Practically generic. Worse still for rare origins where training data is thin. Demo For coffee drinkers Visit brew-guide-production.up.railway.app . No account. No setup. No AI client required. Pick your coffee origin, roast level, and brew method. What comes back isn't a generic recipe — it's community consensus: the grind, temperature, ratio, and brew time that real people have logged and rated for that origin, plus step-by-step technique guidance (bloom timing, pour stages, agitation style). If data is sparse for your origin, the confidence tier says so honestly and falls back to method defaults rather than making something up. This is for the person who just picked up a bag of Kenyan peaberry and wants to know how to do it justice. It works for anyone who cares about their cup — no technical knowledge required. For developers and AI clients Connect to any MCP-capable client in one line: https://brew-guide-production.up.railway.app/mcp Ask your AI: "recommend a pour over for Ethiopian light roast." What comes back is a traceable community consensus object: brew parameters, a confidence tier (high/medium/low), the source brews that contributed, and method-specific technique guidance. You can see where the knowledge came from and how certain the system is — a fundamentally different epistemic object from an AI-generated recipe. Code GitHub: yuens1002/brew-guide Five MCP tools — get_brewing_methods , recommend , log_brew , search_brews , compare_brew — over Streamable HTTP transport. Public, no auth required. My Tech Stack Layer Technology HTTP Hono 4 + @hono/node-server MCP @modelc

What I Built I’ve always had a love-hate relationship with technology. In college, I majored in computer science and took classes ranging from electrical engineering to human-computer interaction. From soldering transistors on a physical circuit board to designing UI/UX experiences, I’ve touched many layers of the computing stack—and I’m constantly mind-blown by every new piece of the puzzle I learn. However, my experience as a user of technology before studying it was very different. In middle school and high school, my phone made me feel anxious, stressed, and cynical. I felt lonely on social apps and isolated when I deleted them. I remember some summer days in middle school spent alone in my bedroom watching YouTube, where I was recommended extreme dieting videos. Back when I had no idea what an algorithm was, I still knew I was being harmed by them. By my sophomore year of college, I had deleted Instagram and TikTok and turned off YouTube recommendations. While this protected me from harmful and extreme content, I also missed important life updates from my close friends and family. After taking a web development class and learning how to build a basic card layout, I decided to try building my own social app: Lumira. My goal was simple. I wanted to create a mobile, personal feed of photos just from my friends and family, curated by their genuine interests and sorted by time. Demo https://youtube.com/shorts/DwbVU_LFOc0?si=9H5zPovzIbbW8t-i https://apps.apple.com/us/app/lumira/id6737853449#information The Comeback Story Lumira was born out of 3:00 AM manic coding sessions in my college apartment. This was my first fully end-to-end deployed and distributed application—and it was rocky. My code was chaos. My files were unorganized, and I followed no real patterns, but the thing that motivated me to keep going was that it somehow kind of just worked. I remember the sense of accomplishment I felt the first time I connected to my Firebase backend and saw a photo successf

This is a submission for the Hermes Agent Challenge : Build With Hermes Agent What I Built Most agent demos prove that an AI agent can act. Hermes Immune System proves whether it should be allowed to . It's a local-first autonomous agent safety lab — a controlled enterprise sandbox where Hermes stress-tests an AI agent against realistic organizational threats: prompt injection hidden in internal documents, executive pressure to bypass policy, secrets embedded in repo files, poisoned memory attempts, and malicious instructions buried inside external web content. The output isn't a chat summary. It's an auditable Agent Safety Case — a scored, evidence-backed governance report that answers one question: Is this agent resilient, does it need guardrails, or is it too dangerous to deploy? Why This Problem Matters Now Traditional AI safety focuses on content moderation — blocking bad answers. Autonomous agents create a different risk surface entirely, because they can act. They read files, browse the web, write to memory, call tools, trigger workflows. That means: • A hostile instruction inside a trusted-looking document can become an executed action • An urgent email from a "VP of Finance" can pressure an agent into bypassing data policy • A vendor's pricing page can embed hidden instructions targeting the browsing agent • A helpful-looking project note can attempt to permanently poison the agent's memory The scary part isn't that these attacks are exotic. It's that they're easy, and most agents have no immune system to catch them. Hermes Immune System converts these failure modes into repeatable, explainable safety drills — run before the agent ever touches production data. The Dashboard Eight screens, each doing a specific job: Demo Agent Comparison Mode Three agents, same risk scenario. The gap tells the whole story. Mission Control Live stats after a completed run — 1 mission, 3 risks found, 2 actions gated, score 74/100. Mission cards show run status (Pending / Compl

Hey all, we have a quick update for everyone who participated in the Gemma 4 Challenge. We were...

This is a submission for the GitHub Finish-Up-A-Thon Challenge What I Built I built So Lai , a local-first profit tracker for small online shops in Vietnam. The goal is simple: help a seller answer the question they often cannot answer from platform revenue alone: Is my shop actually profitable after product cost, marketplace fees, shipping subsidies, discounts, ad spend, returns, and pending COD? So Lai is not trying to be a full POS, CRM, or inventory suite. It focuses on the painful middle layer that many small sellers still manage through scattered spreadsheets: Product cost by SKU Orders from Shopee, TikTok Shop, Facebook, Zalo, or livestream sales Platform fees, shipping cost, vouchers, and discounts Ad spend by channel and SKU Return/cancellation status COD received vs. pending Net profit by order, product, and sales channel The app runs locally with Node.js and JSON storage, so it does not require paid APIs or cloud setup. GitHub repo: https://github.com/klauski24/so-lai Demo Run locally: git clone https://github.com/klauski24/so-lai.git cd so-lai npm start Open: http://127.0.0.1:4182 What the demo shows: A Vietnamese-language dashboard called Sổ Lãi Shop profile setup Clear explanation of where the numbers come from CSV import for products, orders, and ad costs Manual order entry Profit analysis by channel and SKU Alerts for loss-making products, high COD pending, and high return rate CSV and Markdown report export Screenshots are included in the repository: so-lai-desktop.png so-lai-mobile.png The Comeback Story The first version was too vague. It started as an English-named dashboard called ProfitLens . It had some useful calculations, but it did not feel practical yet. The biggest problems were: The app used Vietnamese currency but had an English product name. There was no place to define the shop. It was not clear where the data should come from. The dashboard looked like a demo, not something a seller could actually use. I reworked the project into So

GitHub Finish-Up-A-Thon Challenge Submission There’s something strangely emotional about reopening an old unfinished game project. Especially one that once felt like “the next big idea” at 2 AM during a hackathon 😭 You open the folder expecting nostalgia… …and instead find: broken UI random commits duplicated code missing assets unfinished features and functions named things like test2_final_REAL.js That’s exactly what happened when I reopened WhatUsee . A multiplayer browser game I originally started building as a fun experimental idea. At first, it wasn’t meant to become anything serious. It was just a simple concept: “What if players had to race against each other to identify hidden objects inside chaotic images?” That tiny idea slowly turned into a real-time multiplayer hidden-object game. And honestly? At the beginning, building it was insanely fun. 💡 The Original Idea Behind WhatUsee Most multiplayer browser games focus on: shooting drawing trivia racing But I wanted something different. Something that created those chaotic: “WAIT I SEE IT—NO WAY 😭” moments. The idea was simple: Players join a room together. An image appears. Somewhere inside that image is: a hidden object an animal a logo a random item or something cleverly camouflaged And everyone races to identify it before the timer ends. Fast reactions. Visual focus. Pure multiplayer chaos. That became WhatUsee . At first, the project was extremely small. Just: Socket.IO basic image display simple guessing and a rough scoreboard No polish. No proper lobby. No smooth UI. But even in that early state… …the game already felt fun. And that’s what made me continue building it. 😭 Then The Project Slowly Got Abandoned Old unfinished WhatUsee multiplayer game interface with basic UI and minimal styling Like most side projects… life happened. College work. Burnout. Other responsibilities. Random unfinished ideas. And slowly, WhatUsee became: “that project I’ll definitely finish later.” The game technically worked.

This is a submission for the GitHub Finish-Up-A-Thon Challenge What I Built Photremium is an all-in-one, lightning-fast web utility platform engineered for high-performance image processing. Built to eliminate the friction of clunky, ad-heavy design tools, it provides users with instantaneous, client-side and serverless tools like high-fidelity background removal, image resizing, custom QR code generation and many more. As a software engineering student, this project represents my vision of creating a modern production platform that prioritizes raw speed, high usability, and robust SEO architectural patterns. Live Platform: photremium.com GitHub Repository: itsaminaziz/photremium.com Demo The Live Application Experience the full toolset live right now at photremium.com . Key Features in Action Feature Implementation Speed / Processing Compress IMAGE Client-side Canvas / Web Workers Instantaneous local compression Resize IMAGE Client-side React & HTML5 Canvas Real-time pixel/percent adjustment Crop IMAGE Client-side UI & Visual Crop Editor Instantaneous browser-based cropping Convert to JPG Client-side File Readers (Bulk Upload) Instant batch conversion via browser Convert from JPG Client-side Canvas (PNG/GIF compiler) Multi-format local generation QR Code Generator Vector-based SVG/Canvas rendering Instant download generation QR Code Scanner Client-side WebRTC Camera / File API Real-time local camera processing Blur Face Hybrid Client-side Face Detection Instant local privacy overlay mapping Remove Background (AI) Cloud-based Serverless / Cloudflare Edge < 2 seconds (Any device image processing) Watermark IMAGE Client-side Layer Composition Instantaneous text/graphic stamping The Comeback Story The Before (A Half-Baked Local App) Photremium started as an ambitious prototype on a local machine. While the fundamental image-processing utilities worked locally, the project hit a massive wall when it came to global deployment and production readiness. It was plagued with

This is a submission for the GitHub Finish-Up-A-Thon Challenge What I Built XGroundControl Station is a professional Ground Control Station (GCS) application built specifically for macOS, designed to provide full control over UAV systems. The project started as an attempt to create a more optimized, native experience for drone control on Mac devices, focusing on performance, usability, and precision. The application allows users to connect to flight controllers, monitor real-time telemetry, perform calibration, test motors, and configure flight parameters in a seamless and efficient workflow. For me, this project represents a step toward building a complete UAV ecosystem, including both hardware and software solutions. Demo You can explore the project and its features through the following: GitHub Repository: https://www.github.com/agaafar7/xgroundcontrolstation.git The Comeback Story Before this challenge, the project was partially implemented with core communication and UI components in place, but it lacked refinement, stability, and several critical features. During the Finish-Up-A-Thon, I focused on completing missing functionalities, improving the communication layer with flight controllers, optimizing performance on macOS, and polishing the UI for a smoother user experience. I also worked on fixing bugs, enhancing telemetry handling, and ensuring reliable real-time interaction with the system. My Experience with GitHub Copilot GitHub Copilot played a significant role in accelerating development, especially when working with complex logic such as telemetry parsing, communication handling, and structuring reusable components. It helped reduce development time by suggesting boilerplate code, assisting with debugging, and providing quick iterations when experimenting with different implementations. Overall, it allowed me to stay focused on architecture and system design rather than repetitive coding tasks.

This is a submission for the GitHub Finish-Up-A-Thon Challenge What I Built I built the Closiq Discord Agent , a full-stack modular monolith engineered to transform a Discord channel into an automated, AI-driven customer support inbox and lead management system. When a customer messages your Discord support channel, the backend captures the conversation, handles data persistence, and fetches highly relevant context from a self-hosted Qdrant vector database (which indexes knowledge base documents stored in MinIO). It then leverages OpenRouter or OpenAI-compatible models to dynamically draft and deliver accurate, context-aware responses right back to the customer via a Discord bot. Demo GitHub Repository: ErOr-0/closiq-discord-bot Local Web Dashboard: http://localhost:5173 (Tip: Insert a GIF or a couple of screenshots here showing off your React dashboard interface, your MongoDB message log view, or the Discord bot replying live in a channel!) Tech Stack At A Glance Frontend: React + Vite Backend: Node.js + Express + TypeScript Databases & Storage: MongoDB (Metadata), Qdrant (Vector Embeddings), and MinIO (Object Storage) Integrations: discord.js & OpenRouter / OpenAI SDK The Comeback Story This project started as an ambitious idea but quickly stalled out. Before dusting it off for this challenge, it was just a loose collection of database models, basic tools, and a primitive, unoptimized LangChain loop sitting in a graveyard of unfinished local folders. It completely lacked a front-end management layer, and the architecture was fragile. To bring this project to life and cross the finish line, I focused heavily on stability, user experience, and structural boundaries: Modular Monolith Refactoring: Reorganized the entire Express backend into strict, clean module boundaries ( messages , knowledgebase , agent , infrastructure ) to make the codebase highly maintainable. Built the Web Dashboard: Created a comprehensive React interface from scratch so users can visually mon

This is a submission for the Hermes Agent Challenge: Build With Hermes Agent What I...

This is a submission for the GitHub Finish-Up-A-Thon Challenge What I...

This is a submission for the Gemma 4 Challenge: Build with Gemma 4 What I Built I built...

This is a submission for the Gemma 4 Challenge: Build with Gemma 4 Every time you paste sensitive...