Manav Tyagi Logo PORTFOLIO // CV
Case Studies Download CV

Overview & Architecture Showcase

LOCAL AI PLATFORM ARCHITECTURE // 2026
PREDEFINED LOOKUP: <15ms 100% PRIVATE • OLLAMA REST ENGINE • 0 KB CLOUD EGRESS
Manav A.I. High-Fidelity Local Conversational Assistant Interface
CLICK TO EXPAND // HIGH-RES INSPECT
Manav A.I. — Clean Minimalist Home Stage with Prompt Starters, Live Model Switcher, and Real-Time Heartbeat Guard FIG 00 // HERO SHOWCASE

Manav A.I. is an open-source, ChatGPT-grade conversational assistant designed and engineered by Manav Tyagi to run 100% locally on personal hardware. Powered by an Express.js gateway and Ollama, it bridges local neural models (llama3.1:latest, llama3.2, mistral) with sub-15ms deterministic predefined knowledge matching, on-the-fly model hot-swapping, and an automated heartbeat connection guard that prevents silent daemon failures.

Security: 100% Sovereign Data • Zero External Network Calls Hybrid Intelligence: Cached FAQ + Neural Inference Connection Guard: 2.5s Auto-Reconnecting Polling Stack: Node.js Express • Ollama API • Vanilla JS • CSS Tokens
View Source on GitHub
$ git clone https://github.com/Manav9495/Manav-A.I. && npm start
Interactive Telemetry // Filter By Architectural Discipline CLICK TO FILTER CASE STUDY
FILTERED BY:

The Cloud AI Dilemma & The Local UX Barrier

While modern cloud-hosted generative AI platforms like ChatGPT and Claude transformed knowledge work, they introduced an unsustainable trade-off for software engineers, enterprise teams, and privacy-conscious users: every single prompt, private codebase snippet, and customer document is transmitted across external cloud servers.

Enterprise IP Leaks

Proprietary algorithms, internal API credentials, and client medical/legal records pasted into cloud chats risk third-party data breaches, training-set contamination, and non-compliance with strict regulations (GDPR, HIPAA, SOC 2).

Subscription Fatigue

High recurring per-seat monthly costs ($20–$30/user/month), opaque token rate limits, sudden API throttling during peak hours, and billing shocks restrict continuous exploration and development velocity.

The CLI Usability Barrier

While Ollama brought open-source LLMs to local hardware, raw terminal commands (ollama run) lack conversational history, syntax-highlighted code blocks, copy conveniences, and friendly visual error handling.

THE UI/UX DESIGN OBJECTIVE

Engineering a Consumer-Grade, Sovereign AI Experience on Zero Cloud Infrastructure

The design objective was clear: create a lightweight, responsive web application with the refined aesthetic of ChatGPT, running entirely on a localized Node.js gateway. The system had to guarantee absolute privacy, provide sub-15ms instantaneous responses for common queries through a hybrid deterministic cache, deliver flawless code formatting with one-click copy, and proactively safeguard against local daemon disconnects.

Dual-Engine Intelligence: Cached FAQ + Neural Fallback

Running large language models locally presents a hardware challenge: even on high-end hardware, generating text with an 8-billion-parameter neural network incurs compute latency and power draw. To solve this, Manav Tyagi engineered a Dual-Tier Hybrid Routing Gateway inside backend/server.js.

INFERENCE ROUTING TELEMETRY // PIPELINE DIAGRAM
TIER 1: DETERMINISTIC LATENCY: <15ms

Predefined Knowledge Base (faq.json)

Inbound user prompts are stripped of punctuation and normalized. The gateway matches against an array of trigger phrases. If a match is found, curated responses are served instantaneously.

  • Zero GPU/CPU compute cycles consumed
  • 100% deterministic accuracy for fixed topics
  • Visual pill badge: Predefined Knowledge Base
TIER 2: PROBABILISTIC LATENCY: ~750ms TTFT

Local Ollama Neural Core (/api/chat)

Uncached queries seamlessly drop through to the local Ollama REST daemon. The server injects a custom system persona, prepends multi-turn conversation memory, and streams reasoning back to the client.

  • Context-aware multi-turn reasoning
  • Supports Llama 3.1, Mistral, Gemma 2, DeepSeek
  • Visual pill badge: llama3.1:latest
TECHNICAL BENCHMARKS // ARCHITECTURAL COMPARISON
METRIC COMMERCIAL CLOUD AI CLI OLLAMA (TERMINAL) MANAV A.I. PLATFORM
Data Sovereignty Zero (Sent to external clouds) 100% Local 100% Local (Air-Gapped)
FAQ Lookup Latency 1,200ms – 2,500ms N/A (Full model invocation) <15ms (Deterministic tier)
Cost Structure $20/mo + API usage fees Free & Open Source 100% Free & Open Source
Code Block UX Syntax highlighted + Copy Raw terminal monochrome Syntax highlighted + 1-Click Copy
Daemon Failure Alert 503 Server Error Silent terminal crash 2.5s Pulsing Heartbeat Guard

Conversational Flow, Developer Ergonomics & Connection Guard

A key differentiator of Manav A.I. is its obsessive attention to interaction ergonomics. Rather than treating AI output as plain text, the interface structures code, reasoning, and system states into tactile, high-trust components.

CONVERSATIONAL STAGE // MULTI-TURN MEMORY
ACTIVE REASONING • PREDEFINED BADGES
Manav A.I. Multi-Turn Conversational Reasoning Interface
CLICK TO EXPAND // HIGH-RES INSPECT
Multi-Turn Conversation View: Fluid speech bubble geometry, clear author avatars, and transparent model attribution badges FIG 01 // CONVERSATION FLOW
DEVELOPER EXPERIENCE // SYNTAX HIGHLIGHTING
JETBRAINS MONO • 1-CLICK COPY • LANGUAGE BADGES
Manav A.I. Developer Code Generation and Syntax Highlighting
CLICK TO EXPAND // HIGH-RES INSPECT
Developer Code Block Ergonomics: Custom dark-slate code container, language identification tags, and instantaneous clipboard copy FIG 02 // CODE GENERATION UX
CONNECTION GUARD // REAL-TIME HEARTBEAT
2.5S POLLING • AUTO-RECONNECT • DIAGNOSTIC BANNER
Manav A.I. Real-Time Heartbeat Error Boundary Guard
CLICK TO EXPAND // HIGH-RES INSPECT
Connection Guard Error Boundary: Pulsing red header beacon and actionable terminal recovery guidance when Ollama daemon is offline FIG 03 // ERROR RESILIENCE

Why the 2.5-Second Heartbeat Guard Is Critical for Local AI

Unlike cloud APIs backed by 99.99% server availability, local inference runs on the user's personal operating system. Laptops close, daemons are stopped, or machine memory limits are reached. In traditional web interfaces, this causes infuriating silent failure: users type long prompts only to receive an unresponsive freeze or unformatted console error.

01 • POLLING

Client polls /api/status every 2.5s. If Ollama is unreachable, status dot switches from green to red without page reload.

02 • DIAGNOSTICS

Displays clear recovery instructions (ollama serve) directly in an animated banner, preventing blind user confusion.

03 • AUTO-RECOVERY

The instant the user starts Ollama, the heartbeat detects the socket revival, restores the green state, and unblocks the composer with active history intact.

Live Model Switching & In-App Model Puller

One of the biggest hurdles for open-source AI adoption is model management. Switching between models or downloading new quantizations typically requires switching back and forth between terminal windows and browser tabs. Manav A.I. brings full visual model lifecycle management directly into the web UI.

MODEL CONTROLS // SETTINGS MODAL
IN-APP PULLER • LIVE HOT-SWAP • PARAMETER TUNING
Manav A.I. Model Settings and In-App Puller Dialog
CLICK TO EXPAND // HIGH-RES INSPECT
Visual Model Management Dialog: Real-time model switcher, in-app model downloader, disk footprint stats, and temperature sliders FIG 04 // MODEL CONFIGURATION
Live Dropdown Hot-Swap

Mid-Conversation Switching

Switch between llama3.1:latest for deep coding and llama3.2:3b for rapid creative writing without losing chat state or restarting the server.

In-App Model Puller

Terminal-Free Downloads

Input model identifiers (deepseek-coder, qwen2.5) directly in the UI. The backend calls /api/pull and downloads models to disk with zero command line usage.

Quantization Transparency

Disk & Memory Awareness

Displays exact disk sizes (e.g. 4.7 GB vs 2.0 GB) and modified timestamps, helping users monitor system memory and storage limits effortlessly.

Interactive Interface Gallery & State Inspection

Explore the complete interface and user journey of Manav A.I. Click any screen below to enter the full-screen interactive lightbox inspector with architectural captions and keyboard navigation (← / → / Esc).

Manav A.I. Home Screen Interface
FIG 00 • HOME STAGE
Home Screen: Clean conversational canvas with prompt cards FIG 00
Manav A.I. Conversational Reasoning View
FIG 01 • CONVERSATION
Multi-Turn Chat: Markdown lists, reasoning headers & FAQ tags FIG 01
Manav A.I. Code Generation View
FIG 02 • DEVELOPER UX
Code Block: Monospace typography, syntax styling & copy toast FIG 02
Manav A.I. Model Settings Dialog
FIG 03 • MODEL SETTINGS
Model Settings: Dropdown selector, in-app puller & temperature FIG 03
Manav A.I. Connection Guard Error State
FIG 04 • CONNECTION GUARD
Connection Guard: Heartbeat daemon polling with pulsing red beacon and terminal guidance FIG 04

Engineering Benchmarks, Privacy Guarantees & Takeaways

By pairing an accessible, consumer-grade conversational UX with a lightweight local Express proxy and deterministic FAQ matcher, Manav A.I. demonstrates that data sovereignty and delightful design are not mutually exclusive.

0.00 KB
Cloud Egress

Zero packets sent to external corporate servers. Air-gapped compliance.

<15ms
Predefined FAQ Latency

Instant responses for common queries without GPU wake-up delays.

2.5s
Heartbeat Guard Cycle

Real-time socket healthcheck with auto-reconnection and zero chat loss.

$0.00
API / Subscription Cost

100% free, MIT licensed, open-source software running on owned hardware.

Key Architectural & UI/UX Takeaways

• Deterministic Caching + Neural Flexibility: The combination of an exact-match knowledge base (faq.json) paired with an LLM fallback is an architecture every enterprise AI interface should adopt. It delivers sub-15ms speed for common intents while preserving open-ended intelligence.

• Proactive Error Boundaries Over Reactive Alerts: In local client-side software, polling service health before the user hits submit prevents 100% of broken prompt attempts and fosters trust.

• Zero-Dependency Lightweight Footprints: Rather than forcing users to spin up heavy Docker containers or complex React/Next.js frameworks, a pure vanilla client served directly by Express ensures 100% platform portability and instant startup.

OPEN-SOURCE ON GITHUB

Explore the Manav A.I. Codebase

MIT Licensed • Complete Express server, FAQ matcher, and vanilla client controller

Star on GitHub
Previous: Canopy Paws (Mobile Pet Tech) Next: Ayushi Elevators (Enterprise Configurator)