K cha khabar
Nepal news intelligence.
AI-clustered stories with bilingual summaries, ownership transparency across 35+ Nepali publishers, and trending topics. Headlines only — every item links back to the source.
- News intelligence
- AI clustering
- Bilingual
- Public good
- Publishers tracked
- 35+
- Headlines indexed
- 6,550+
- Languages
- नेपाली · English
- Embeddings
- BGE-M3
The story
What it is and why we built it
K cha khabar (के छ खबर?, colloquial Nepali for "What's the news?") is a news intelligence layer for Nepal's fragmented press. It aggregates and clusters Nepali- and English-language headlines from 35+ publishers, then surfaces them as bilingual AI-generated story digests with full publisher attribution and ownership labels.
It's deliberately a headline-and-excerpt aggregator — never republishing full articles. Multilingual clustering uses BGE-M3 embeddings with a 0.78 cosine similarity threshold to detect when multiple outlets are covering the same story. Bilingual summaries are drafted independently per language so the Nepali version reads natively, not as a translation of the English one.
Every publisher carries an ownership label (state, private, independent, non-profit) so readers can weigh perspective. Built for the 1.5M+ strong Nepali diaspora, in-country readers wanting cross-publisher view, and researchers studying the Nepali media ecosystem.
What's inside
Features
- 01
AI story clustering
BGE-M3 multilingual embeddings (1,024-dim, ≥0.78 cosine threshold) detect when 3+ outlets are covering the same story so you see one story, not ten copies.
- 02
Bilingual summaries, drafted independently
Nepali and English summaries are written natively per language — not machine translations of each other — so the Nepali reads like Nepali.
- 03
Publisher ownership labels
Every headline carries an ownership badge — state, private, independent, non-profit — so you can weigh perspective at a glance.
- 04
Cross-publisher echo detection
Stories surface once they cross a breadth threshold so quiet single-source pieces don't drown out the wider conversation.
- 05
Named-entity awareness
A curated registry of Nepali politicians, organisations, and places — including time-bounded role assignments like the current PM — keeps tagging accurate.
- 06
Headlines only — links go to source
No republished articles, no ads, no comments section. Every item links back to the original publisher.
Who it's for
Built for
- The 1.5M+ strong Nepali diaspora across Australia, US, UK, and the Gulf
- Politically engaged in-country readers wanting a cross-publisher view
- Journalists, academics, and NGOs studying the Nepali media ecosystem
- Anyone who's tired of refreshing 12 news sites at once
How it's different
Differentiators
- Independently-drafted bilingual summaries — not translations.
- Publisher ownership labels are surfaced on every headline (rare in any market, unique for Nepal).
- Multilingual clustering across Devanagari and Latin scripts, no transliteration required.
- Deliberate headlines-only stance: links always go back to source.
- Hosted outside Nepal as a stated press-freedom hedge.
Frequently asked
Common questions
Why "headlines only"?
How do you decide what's a "story"?
Are the summaries machine-translated?
How do you handle ownership transparency?
Is it free?
Pricing
Free · ad-free · no paywall
Stack
Next.js · BGE-M3 embeddings · Custom NER · RSS + sitemap ingestion · Multilingual clustering
Resources
Like the way we build kchakhabar? Let's build for you.
The same team and standards that built kchakhabar are available for your project. We'd love to chat.