') + ')', 'gi'); if (regex.test(text)) { found = true; var frag = document.createDocumentFragment(); var parts = text.split(regex); parts.forEach(function(part, i) { if (i % 2 === 0) { frag.appendChild(document.createTextNode(part)); } else { var span = document.createElement('span'); span.className = 'userscript-highlight'; span.textContent = part; frag.appendChild(span); } }); node.parentNode.replaceChild(frag, node); } }); } else if (node.nodeType === 1 && node.childNodes) { // element var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT']; if (!skipTags.includes(node.tagName)) { Array.from(node.childNodes).forEach(highlight); } } } highlight(document.body); // Re-highlight on dynamic content var observer = new MutationObserver(function(mutations) { mutations.forEach(function(m) { m.addedNodes.forEach(function(node) { if (node.nodeType === 1 || node.nodeType === 3) highlight(node); }); }); }); observer.observe(document.body, { childList: true, subtree: true }); })(); } } catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + ', 'i'); if (__m === '*' || __re.test(location.href)) { // Strip utm_, fbclid, gclid, etc. from all links on page (function() { var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content', 'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid', 'ref', 'ref_src', 'source', 'medium', 'campaign']; function cleanUrl(url) { try { var u = new URL(url, window.location.origin); var changed = false; trackingParams.forEach(function(p) { if (u.searchParams.has(p)) { u.searchParams.delete(p); changed = true; } }); return changed ? u.toString() : url; } catch (e) { return url; } } function cleanLinks() { document.querySelectorAll('a[href]').forEach(function(a) { var clean = cleanUrl(a.href); if (clean !== a.href) a.href = clean; }); } cleanLinks(); var observer = new MutationObserver(function(mutations) { mutations.forEach(function(m) { m.addedNodes.forEach(function(node) { if (node.nodeType === 1) { if (node.tagName === 'A') cleanLinks(); node.querySelectorAll('a[href]').forEach(function(a) { var clean = cleanUrl(a.href); if (clean !== a.href) a.href = clean; }); } }); }); }); observer.observe(document.body, { childList: true, subtree: true }); })(); } } catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); } })(); (function(){ try { var __m = "youtube.com"; var __re = new RegExp('^' + "youtube\\.com" + ', 'i'); if (__m === '*' || __re.test(location.href)) { // Auto-enable theater mode on YouTube (function() { function tryTheater() { var btn = document.querySelector('button[aria-label="Theater mode"], ytd-player #player button[title="Theater mode"]'); if (btn && !btn.classList.contains('activated')) { btn.click(); } } // Try immediately tryTheater(); // Try after navigation (SPA) var lastUrl = location.href; setInterval(function() { if (location.href !== lastUrl) { lastUrl = location.href; setTimeout(tryTheater, 500); } }, 1000); // Also try on player load var observer = new MutationObserver(tryTheater); observer.observe(document.body, { childList: true, subtree: true }); })(); } } catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + ', 'i'); if (__m === '*' || __re.test(location.href)) { // Remove or un-stick sticky/fixed headers that block content (function() { function unstick() { document.querySelectorAll('header, nav, [role="banner"], .header, .navbar, .sticky, .fixed-top, [style*="position: fixed"], [style*="position:sticky"]').forEach(function(el) { if (el.style.position === 'fixed' || el.style.position === 'sticky' || getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') { el.style.position = 'static'; el.style.top = 'auto'; el.style.zIndex = 'auto'; } }); } unstick(); var observer = new MutationObserver(unstick); observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] }); })(); } } catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); } })(); })(); GitHub - LGEaston/RepLog · GitHub
Skip to content
BranchesTags

Latest commit

History

55 Commits

Folders and files

NameName
Last commit message
Last commit date
bob_sessions
bob_sessions
public
public
server
server
src
src
.gitignore
.gitignore
NOTES_DASHBOARD_IMPLEMENTATION_SUMMARY.md
NOTES_DASHBOARD_IMPLEMENTATION_SUMMARY.md
NOTES_DASHBOARD_PLAN.md
NOTES_DASHBOARD_PLAN.md
NOTES_DASHBOARD_QUICKSTART.md
NOTES_DASHBOARD_QUICKSTART.md
NOTES_DASHBOARD_README.md
NOTES_DASHBOARD_README.md
NOTES_DASHBOARD_TEST_GUIDE.md
NOTES_DASHBOARD_TEST_GUIDE.md
NOTES_DASHBOARD_VISUAL_GUIDE.md
NOTES_DASHBOARD_VISUAL_GUIDE.md
README.md
README.md
RepLog_Hackathon_Submission.docx
RepLog_Hackathon_Submission.docx
Replog Demo.mp4
Replog Demo.mp4
eslint.config.js
eslint.config.js
index.html
index.html
package-lock.json
package-lock.json
package.json
package.json
ping.js
ping.js
test.js
test.js
vite.config.js
vite.config.js

Repository files navigation

RepLog. 🦾✨

The AI-Powered Coaching Journal for Elite Athletes and Creators.

RepLog is a high-performance web application designed for the IBM WatsonX Hackathon 2026. It transforms raw practice logs into actionable coaching intelligence, powered by IBM's industry-leading Granite Foundation Models.

📽️ Project Overview

In a world of data overflow, athletes and creators often struggle to turn "practice volume" into "performance progress." RepLog bridges this gap by acting as a 24/7 AI coach. By analyzing training logs, sensory feedback, and performance metrics, RepLog provides structured, psychological, and technical feedback to help users achieve their "Peak Rep."

🎨 Design Philosophy: Glassmorphism 2.0

RepLog features a bespoke Glassmorphic UI designed for focus and flow:

  • Ultra-Modern Aesthetics: Translucent layers with dynamic blur effects and vibrant gradients.
  • Micro-Animations: Subtle transitions that provide tactile feedback without distraction.
  • Mobile First: Responsive architecture that works on the track, in the gym, or at the desk.

🚀 Core Features

🧠 IBM WatsonX "Bob" AI Coach

  • Granite-Powered Insights: Leveraging ibm/granite-3-8b-instruct to perform domain-specific analysis across sports, coding, and music.
  • Structured Coaching Loop: Every response follows a high-impact pattern:
    • 🎉 Small Wins: Immediate positive reinforcement.
    • 🔍 Pattern Observation: Identifying technical or mental trends.
    • 🎯 Next Practice Focus: Concrete, actionable steps for the next session.
  • Semantic Auto-Titling: Bob analyzes the start of your session and automatically generates a title to keep your history organized.

🧵 Multi-Session Architecture

  • Parallel Threads: Maintain separate coaching sessions for "Cardio," "Strength," and "Skill Work" simultaneously.
  • Persistence: For registered users, sessions are preserved across reloads with optimized local caching.
  • Session Management: Full control to resume, jump back to history, or delete old sessions.

📚 Professional Markdown Notebook

  • Drag-&-Drop Intelligence: Seamlessly drag coaching advice or previous logs directly into your persistent journal.
  • Read-Only for Guests: Default welcome guides are provided as read-only templates to ensure system integrity.
  • User-Scoped Storage: Implements prefix_userEmail storage logic to ensure multi-user data isolation on shared machines.

🛠️ Technical Architecture

Frontend: The High-Fidelity Interface

  • React (Vite): Lightning-fast HMR and build times.
  • Vanilla CSS: Custom design system built from the ground up (no generic frameworks).
  • Lucide Icons: Crisp, medical-grade iconography for professional appearance.
  • React-Markdown: Full support for GFM-enhanced coaching summaries.

Backend: The WatsonX Pipeline

  • Node.js / Express: Secure proxy layer to mask API credentials.
  • IBM WatsonX AI SDK: Direct integration with @ibm-cloud/watsonx-ai.
  • Robust Parsing Engine: Custom regex-based JSON extractor that handles truncated or malformed LLM responses gracefully.

🏁 Getting Started

1. Prerequisites

  • Node.js v18 or higher.
  • IBM Cloud Account with a WatsonX.ai project instance.

2. Deployment Setup

Create a .env file in the root directory:

IBM_CLOUD_API_KEY=your_ibm_api_keyIBM_PROJECT_ID=your_watsonx_project_idPORT=3001

3. Installation & Launch

# 1. Install dependencies
npm install
# 2. Launch the AI Backend (Terminal 1)
node server/index.js
# 3. Launch the Frontend (Terminal 2)
npm run dev

📖 Feature Guides

🏆 Hackathon Submission Notes

  • Innovation: Real-time conversion of unstructured practice logs into structured coaching plans.
  • Reliability: Implements robust error handling for AI inference and secure authentication workflows.
  • Scalability: Designed for multi-user expansion while maintaining strict data privacy via user-scoped storage.

Created with 🦾 by Team Vireon for the IBM WatsonX Hackathon 2026. "Optimize every rep. Log every gain."

About

No description, website, or topics provided.

Resources

Readme
Activity

Stars

0 stars

Watchers

0 watching

Forks

0 forks
Report repository

Releases

Packages

Contributors

Languages