akitaonrails

akitaonrails / frank_investigator

Public

An attempt at a news audit system to analyze biased or even fake journalism [in development]

16
2
100% credibility
Found Mar 26, 2026 at 16 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Ruby
AI Summary

Frank Investigator is an open-source web app that fact-checks news articles by extracting claims, tracing citations to primary sources, assessing them via AI consensus, and highlighting biases or omissions.

How It Works

1
📰 Find a news story

You spot an article online and wonder if its claims hold up.

2
🌐 Visit Frank Investigator

Head to the website where anyone can submit articles for checking.

3
🔍 Paste the link

Type or paste the article's web address and hit investigate to start the check.

4
⏳ Watch it work

See live updates as it reads the story, finds key facts, and chases down sources.

5
📊 Review the facts

Check ratings for each claim, source quality, and any tricks like hype-y headlines.

✅ Get the truth

Walk away knowing which parts are solid, weak, or missing important context.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 16 to 16 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is frank_investigator?

Frank Investigator is a Ruby on Rails app that audits news articles for bias and fakery—paste a URL like trump assassination attempt newspaper coverage or assassination attempt news today, and it fetches the page, extracts verifiable claims, builds evidence graphs from primary sources, and delivers confidence scores via multi-LLM consensus. It flags echo chambers, headline bait, rhetorical fallacies, and omissions, with live updates in a server-rendered dashboard using Turbo Streams. Deployable via Docker, it prioritizes authority over volume, capping confidence if primaries dispute claims.

Why is it gaining traction?

Unlike generic fact-checkers, it detects circular citations and unsubstantiated viral patterns in coup attempt news or neet attempt news, weighting independence and staleness—perfect for dissecting frank private investigator-style echo chambers across US and Brazil outlets. Devs dig the one-command setup (bin/setup, bin/dev) and production Docker push (bin/deploy), plus JSON APIs for embedding in apps. Its "truth over consensus" rules cut through volume-based manipulation without manual tweaks.

Who should use this?

Political analysts verifying trump attempt news or upsc attempt news bias, independent journalists auditing sensational headlines like frank cannon private investigator exposes, or backend devs building news aggregators needing automated claim assessments. Ideal for Brazil-focused teams profiling G1/Folha vs. VEJA/Gazeta do Povo, or anyone scripting github attempt merge pipelines with run_attempt github checks.

Verdict

Promising early prototype for automated news audits (16 stars, solid README/Docker setup, full tests), but 1.0% credibility score signals heavy dev-in-progress risks—fork and harden it if custom fact-checking fits your stack, otherwise monitor for maturity.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.