Choose how summaries and Q&A are generated. Local runs Gemma in your browser via WebGPU — first load downloads ~1.5 GB of weights, cached after.
Adds the option to enrich Ask answers with recent web results. Without this, Ask uses only the report itself. All providers support free tiers; key stays in this browser.
—
📘 New here? Open the full user guide → — covers AI setup, BYOK costs/limits, web search enrichment, privacy details.
A single-file browser app to browse, search, and summarise reports from India's 24 Departmentally Related Standing Committees (DRSCs) — 16 chaired by Lok Sabha, 8 by Rajya Sabha. The reports are scraped daily from sansad.in and mirrored as static JSON/text on GitHub Pages so this page can read them with no server, no auth, no API key.
DRSCs are the most robust institutional mechanism through which Indian Parliament scrutinises the executive. Their reports — on demands for grants, bills, and policy subjects — are evidence-based and non-partisan. They're also poorly indexed and rarely read.
Open any report and you get four tabs: Details (metadata + PDF links), Full text (when extracted), AI summary (one click → plain-English briefing), and Ask (chat with the report). AI runs on your device by default — open Settings (the gear icon, top right) to load a model or set a BYOK key. Full walkthrough in the user guide.
Runs Gemma 4 (E2B or E4B) entirely in your browser via WebGPU. The first load downloads weights from Hugging Face (~1.5 GB for E2B, ~4.9 GB for E4B); subsequent loads are instant from your browser cache. Requires a recent Chrome/Edge or Firefox 130+ with a compatible GPU. No data leaves your device.
If WebGPU isn't available or you want a stronger model, configure a provider in Settings. Free options:
ollama pull llama3.2 then enable CORS for browsers.Paid: Anthropic (best summaries) at console.anthropic.com, OpenAI at platform.openai.com.
localStorage, never sent anywhere except your chosen provider)IndexedDB)naklitechie.github.io/parliamentwatch-data/ — static JSON + text files. No tracking.huggingface.co — model weights, only on first Gemma load.index.html from GitHub Pages.The scraping logic, committee config, API map, and the original idea are all from ParliamentWatch by Pranay Kotasthane. The scraper.py, pdf_utils.py, and config.py in the data-mirror repo are vendored from his project. SansadLocal repackages it as a single HTML file with on-device AI; the data engine underneath is his.
Chirag Patnaik (NakliTechie) — part of a series of single-file browser-native tools.