Skip to content
Moat or Bloat

Negarit Gazette V2

PDF parser and text extractor for Ethiopian Negarit Gazeta proclamations using Google's Gemini 2.0 Flash API

Web app Rated 7 Oct 2026Dormant

Link
negarit-gazette.web.app
Built by
Found This

Bloat

121/500

Where it landed on the scale

Bloat
0
Float
300
Moat
400

Summary

A working, live, open-source archive of Ethiopian proclamations from 1995 onward, with bilingual search and an Amharic language toggle. It is a real, useful public resource, but it has no business model, no sign of users paying, and little to stop a copy beyond the effort of cleaning the data. It has had no activity for over a year since the single launch post.

Bloat · Not much here works or looks likely to last, yet.

Breakdown

Five measures, 100 points each. Open the receipts under any of them to see the posts and pages behind the points.

Viability

Is there a real problem, someone who would pay, and a market this builder can actually reach?

There is a real problem (Ethiopian legal texts are hard to search and reuse), but nothing shows a path to payment. It is a free public-good archive with no pricing or monetisation.

28/100

Rubric 21–40A real problem, but no plausible path to anyone paying, or a market well out of this builder's reach.

Receipts (2)

  1. Frames the project as a free, open-source resource and a dataset for AI training, with no mention of customers or charging.

    “There was some chatter on Hacker News recently about Google's Gemini 2.0 Flash model and how it’s really good at parsing PDFs, so I tried it and it was really good. I used a Negarit Gazeta PDF that has English and Amharic text side by side. Gemini Flash extracted the text based on the format I wanted, plus gave me each language separately. That’s when I decided to revive an old project after 4 yea”

    Post · @found_this · 29 Mar 2025 · open on Telegram (opens in a new tab)

  2. The site is a free browsable archive of proclamations with no pricing, accounts or payments.

    Checked 7 Oct 2026 · negarit-gazette.web.app (opens in a new tab)

Moat

What stops someone copying it?

The edge is mostly execution: the PDFs come from Open Gazeta and the extraction is a Gemini API call that others could repeat. Cleaned, corrected bilingual text could become a modest dataset advantage if it keeps growing, but that has not yet compounded.

22/100

Rubric 21–40The only edge is execution, or being first.

Receipts (2)

  1. Relies on a third-party model (Gemini 2.0 Flash) and publicly sourced PDFs, and admits manual corrections are still needed.

    “There was some chatter on Hacker News recently about Google's Gemini 2.0 Flash model and how it’s really good at parsing PDFs, so I tried it and it was really good. I used a Negarit Gazeta PDF that has English and Amharic text side by side. Gemini Flash extracted the text based on the format I wanted, plus gave me each language separately. That’s when I decided to revive an old project after 4 yea”

    Post · @found_this · 29 Mar 2025 · open on Telegram (opens in a new tab)

  2. Standard Astro Starlight site, easy to reproduce; the value is in the converted content.

    Checked 7 Oct 2026 · negarit-gazette.web.app (opens in a new tab)

Momentum

Did the updates keep coming?

Shipped once, as a revival of an older project, on 2025-03-29, with no updates in the 557 days since. Momentum is effectively nil.

0/100

  • Sustained shipping0/60

    Worked on across 0 days.

  • Consistency0/40

    Updates in 1 of 1 month.

  • Quiet

    No update for 557 days — scaled to 20%.

Receipts (1)

  1. Earliest post about it.

    “There was some chatter on Hacker News recently about Google's Gemini 2.0 Flash model and how it’s really good at parsing PDFs, so I tried it and it was really good. I used a Negarit Gazeta PDF that has English and Amharic text side by side. Gemini Flash extracted the text based on the format I wanted, plus gave me each language separately. That’s when I decided to revive an old project after 4 yea”

    Post · @found_this · 29 Mar 2025 · open on Telegram (opens in a new tab)

Infrastructure

Does a real, working product exist?

A real, working site exists with hundreds of proclamations, search and bilingual navigation, but it is a static archive with partial coverage and some unfixed extraction errors.

54/100

  • It's live20/20

    https://negarit-gazette.web.app/ responded when checked.

  • HTTPS5/5

    Served over HTTPS.

  • Real product25/35

    The site works and has hundreds of proclamations indexed by year, with search and English/Amharic switching. It is thin because it is a static document site with partial coverage and uncorrected extraction errors.

  • Own home0/10

    Only on a free subdomain or link-in-bio page.

  • Maintained0/15

    Last sign of shipping 2025-03-29.

  • Operations4/15

    Open-source repos and Firebase hosting exist, but there are no accounts, API, docs, status page or other platforms.

Receipts (5)

  1. https://negarit-gazette.web.app/ responded when checked.

    Checked 7 Oct 2026 · negarit-gazette.web.app (opens in a new tab)

  2. Live site lists proclamations for 1995–1998 and beyond, with search and a language selector.

    Checked 7 Oct 2026 · negarit-gazette.web.app (opens in a new tab)

  3. Creator says some results still need manual corrections and only some years are converted.

    “There was some chatter on Hacker News recently about Google's Gemini 2.0 Flash model and how it’s really good at parsing PDFs, so I tried it and it was really good. I used a Negarit Gazeta PDF that has English and Amharic text side by side. Gemini Flash extracted the text based on the format I wanted, plus gave me each language separately. That’s when I decided to revive an old project after 4 yea”

    Post · @found_this · 29 Mar 2025 · open on Telegram (opens in a new tab)

  4. Facts show no accounts, docs or status page; two repo links are present.

    Checked 7 Oct 2026 · negarit-gazette.web.app (opens in a new tab)

  5. Hosted on Firebase, with the code on GitHub.

    “There was some chatter on Hacker News recently about Google's Gemini 2.0 Flash model and how it’s really good at parsing PDFs, so I tried it and it was really good. I used a Negarit Gazeta PDF that has English and Amharic text side by side. Gemini Flash extracted the text based on the format I wanted, plus gave me each language separately. That’s when I decided to revive an old project after 4 yea”

    Post · @found_this · 29 Mar 2025 · open on Telegram (opens in a new tab)

Sustainability

Is it being set up to last?

Distribution is a free-subdomain site, and there is no pricing, payment, privacy or terms page, so no money path. The creator voiced intent to expand, but nothing since the launch backs that up.

17/100

  • Distribution12/30

    A site on a free subdomain.

  • Payments0/15

    No payment provider found.

  • Pricing0/10

    No pricing found on the site.

  • Revenue0/5

    No revenue or paying customers are mentioned, and the project is free.

  • Privacy policy0/7

    No privacy policy found.

  • Terms0/5

    No terms of service found.

  • Support0/8

    No support contact found.

  • Commitment5/20

    The creator revived a four-year-old project, invites contributions and says more proclamations are planned. But there is no dedicated channel, no team, and no activity since the launch post.

Receipts (4)

  1. A site on a free subdomain.

    Checked 7 Oct 2026 · negarit-gazette.web.app (opens in a new tab)

  2. No mention of customers, revenue or pricing.

    “There was some chatter on Hacker News recently about Google's Gemini 2.0 Flash model and how it’s really good at parsing PDFs, so I tried it and it was really good. I used a Negarit Gazeta PDF that has English and Amharic text side by side. Gemini Flash extracted the text based on the format I wanted, plus gave me each language separately. That’s when I decided to revive an old project after 4 yea”

    Post · @found_this · 29 Mar 2025 · open on Telegram (opens in a new tab)

  3. States plans to add more proclamations and regulations and asks for contributions.

    “There was some chatter on Hacker News recently about Google's Gemini 2.0 Flash model and how it’s really good at parsing PDFs, so I tried it and it was really good. I used a Negarit Gazeta PDF that has English and Amharic text side by side. Gemini Flash extracted the text based on the format I wanted, plus gave me each language separately. That’s when I decided to revive an old project after 4 yea”

    Post · @found_this · 29 Mar 2025 · open on Telegram (opens in a new tab)

  4. The crawler found no support contact and no further shipping after 2025-03-29.

    Checked 7 Oct 2026 · negarit-gazette.web.app (opens in a new tab)