Skip to content

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

🧠 Lam — The Ultra-Intelligent Frontend PC Diagnostic Tool

Lam is a one-of-a-kind, question-focused, browser-based diagnostic system that thinks, reasons, and evolves like a top-tier systems engineer. Built entirely using HTML, CSS, and JavaScript — no backend, no external APIs — Lam simulates human-like troubleshooting intelligence to deliver highly probable, explainable PC problem diagnoses.


🌟 Key Features

🧠 Cognitive Diagnostic Engine (CDE)

A core module that simulates metacognitive problem-solving:

  • Adaptive questioning using Bayesian inference and fuzzy logic
  • Confidence scoring that updates in real time
  • Multisymptom correlation (e.g., “freezes + noises + Event ID 51”)

🧬 Persona-Based Diagnostic Modes

Switch between expert personas for domain-specific insight:

  • Hardware Hermit – Power, thermal, and physical-level faults
  • OS Oracle – Deep system internals, drivers, event logs
  • Network Ninja – IP stack failures, DNS, adapter issues
  • Forensics Falcon – Malware, behavioral anomalies, stealth issues

Each persona customizes the diagnostic path, questioning tone, and logic hierarchy.


📊 Diagnostic Storyline UI

A unique interface inspired by crime-solving timelines:

  • Live-updating diagnosis probability graphs
  • Breadcrumb trail of user responses and Lam’s interpretations
  • “What If” simulation mode for alternate scenario modeling
  • Visual explanation of every decision and next step

🤖 Humanlike Interaction & Socratic Reasoning

  • Clarifying sub-questions based on ambiguity detection
  • Emotion-aware UI cues (frustration, urgency, confusion)
  • Natural language pattern recognition (e.g., “it acts weird when I open Chrome”)
  • Deep transparency: ask Lam “Why this question?” at any point

⚙️ Offline-First Architecture (PWA)

Lam runs 100% client-side:

  • Fully functional offline as a Progressive Web App
  • Uses Service Workers to cache diagnostic models and UI assets
  • LocalStorage saves session history, user decisions, and confidence shifts
  • Sessions exportable as JSON or PDF for technicians

🧠 Intelligence Meta-Mode (Optional)

Peek inside Lam’s “mind”:

  • Real-time logic tree with weighted decisions
  • Confidence heatmap of possible issues
  • Internal monologue simulator (“Based on the PSU age and error timeline…”)
  • Self-corrective reasoning: changes path if assumptions fail

🚀 Tech Stack

  • HTML5 — Clean semantic structure
  • TailwindCSS — Apple-level minimalist UI/UX
  • Vanilla JavaScript (ES6+) — Modular expert systems, decision trees, and inference logic
  • JSON — Diagnostic knowledge base, persona modules, and logic graphs
  • Service Workers — Full offline PWA support
  • LocalStorage — State persistence and historical analysis

📦 Coming Soon

  • 🔌 Plugin system to add community-made diagnosis modules
  • 🌐 RTL interface support for Arabic and other languages
  • 🔍 Smart scanner (experimental): real-time system feedback parser using Web APIs
  • 🧠 Learn Mode: teaches users basic troubleshooting as they answer questions

🤯 Vision

Lam is not just a tool — it’s a digital diagnostician.
It merges the logical rigor of a technician, the curiosity of a doctor, and the design elegance of a creative visionary — all running in your browser.


🛠️ Setup

No installation needed. Just open index.html in your browser.

To install Lam as a PWA:
Click the install icon in your browser (available in Chrome, Edge, etc.) for offline access.


🧑‍💻 Made by Omar

Inspired by the genius of cognitive systems, cyber forensics, and human intuition.


📄 License

MIT License – Feel free to use, remix, or enhance Lam for your own projects.


About

Lam is a cutting-edge, browser-based AI diagnostic tool that uses advanced question-driven logic, parallel expert personas, and self-evolving intelligence to accurately diagnose PC issues

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages