Skip to content

NyayaSetu

Offline-First AI Governance Platform for Rural India

RoleFull-Stack AI Engineering, Agentic Systems Design, NLP Architecture & Academic Research
Built byShaurya Punj
LocationIndia
Year2025 - 2026
NyayaSetu hero

Overview

NyayaSetu (न्यायसेतु - "Bridge to Justice") is a production-grade, multilingual AI governance platform designed for rural Indian citizens and government officers with limited or no internet connectivity. It provides voice-native, Hindi/English/Hinglish access to government schemes, grievance routing, and notice management through local LLM inference - no cloud dependency required.

Access on Request

Not publicly deployed.

Book a 20-minute private walkthrough and I will run the whole system end-to-end: architecture, code path, live UI, and the edge cases that shaped it.

Book a private demo

The Problem

Over 833 million rural Indians lack reliable internet access, yet the delivery of government welfare schemes, grievance redressal, and public notices has moved almost entirely online. Approximately 313 million adults in India cannot read or write, making text-only digital portals effectively inaccessible. Fewer than 30% of eligible beneficiaries successfully access entitlements they qualify for, due to language barriers, connectivity gaps, and complex bureaucratic interfaces.

The Solution

NyayaSetu deploys entirely on-device using Ollama-managed local LLMs (Qwen2.5-14B for structured reasoning, Sarvam-optimized models for Indic language understanding), a FAISS vector store for semantic scheme search, and Helsinki-NLP multilingual embeddings - all without requiring internet. Citizens interact via voice in Hindi, English, or Hinglish; NyayaVaani transcribes speech with faster-whisper, routes queries through a RAG pipeline, generates contextual answers, and responds via Coqui TTS - completing the full loop offline.

Project Walkthrough

Agent Architecture

01

NyayaVaani - Voice Intelligence Engine

InputSpoken query in Hindi / English / Hinglish
Enginefaster-whisper → Qwen2.5-14B / Sarvam 24B → Coqui TTS
OutputSpoken answer in user's language + structured text
Speed: ~3-6s offline
02

RAG Scheme Intelligence Engine

InputNatural language query (text or transcribed speech)
EngineHelsinki-NLP embeddings → FAISS vector search → Qwen2.5-14B
OutputGrounded scheme answer with source attribution
Speed: ~1.5-4s
03

Grievance Router

InputCitizen grievance text / voice submission
EngineQwen2.5-14B classification → SLA assignment → SQLite
OutputCategorized ticket routed to correct department
Speed: < 2s
04

Scheme Summarizer

InputRaw government scheme document (PDF / text)
EngineQwen2.5-14B structured summarization with JSON output
OutputCitizen-friendly summary with eligibility & steps
Speed: ~5-10s
05

Notice Drafter

InputOfficer intent / template + auto-filled credentials
EngineQwen2.5-14B generation with role context injection
OutputFormal government notice draft ready for review
Speed: ~3-7s

System Architecture

NyayaSetu architecture flowchart

Technology Stack

client

  • React 18
  • TypeScript
  • Electron (Desktop)
  • HashRouter (Offline SPA)

server

  • FastAPI (Python)
  • SQLite (Offline-First)
  • REST API + OpenAPI Docs

ai

  • Ollama (Local LLM Runtime)
  • Qwen2.5-14B
  • Sarvam 24B (Indic Intelligence)
  • faster-whisper (Offline ASR)
  • Coqui TTS (Offline Synthesis)
  • FAISS Vector Search

data

  • SQLite (All Persistence)
  • FAISS Vector Index
  • Government Scheme PDFs
  • In-Memory Cache (280x Speedup)

Key Features

01

Fully offline - all LLM inference runs locally via Ollama, zero cloud dependency

02

Voice-native multilingual interface: Hindi, English & Hinglish supported

03

RAG-powered scheme discovery grounded in real government documents

04

Role-based access: citizen self-service vs officer admin panel

05

Grievance routing with department assignment and SLA monitoring

06

AI-assisted notice drafting with officer credential auto-fill

Screenshots

Project Presentation

10 slides

Full walkthrough — Bridge of Justice deck covering the problem space, system architecture, agent pipelines, and real-world impact for NyayaSetu.

Download deck PDF