I got tired of waiting for Big Tech to build Deep Research that actually works.
So I built it myself. Today I'm releasing Lutum Veritas - an open source Deep Research Engine.
What it does:
Transforms any question into 200,000+ character academic research documents
Recursive pipeline where each research point knows what previous ones discovered
Claim Audit Tables force the model into self-reflection instead of blind assertions
Camoufox scraper cuts through Cloudflare and paywalls with 0% detection rate
Cost: Under $0.20 per research. OpenAI o3 equivalent: $7.36.
That's not a typo. 92x cheaper. Deeper output. Full transparency.
This isn't an "alternative" to Perplexity or ChatGPT. This is proof that a solo dev with the right architecture can beat billion-dollar corporations at what should be their core competency: deep, verifiable knowledge.
Perplexity, OpenAI and Google deliver summaries. I wanted truth.
So I stopped waiting and built it myself. The Camoufox scraper cuts through Cloudflare, Bloomberg and paywalls with 0% detection. The recursive pipeline passes context forward – each research point knows what the previous ones discovered. Claim Audits force the model into self-reflection instead of blind assertions.
The result: 203,000 characters of academic depth for a single query. Cost: under 20 cents. That's orders of magnitude cheaper than OpenAI o3 and qualitatively in a different league.
This isn't an "alternative" to existing tools. This is proof that a solo dev with the right architecture can beat billion-dollar corporations at what should be their core competency: deep, verifiable knowledge.
The bar for Deep Research is set right here.
— Martin Gehrken, January 30, 2026
AGPL-3.0 licensed. Because truth shouldn't be locked behind paywalls.
🔗 GitHub: https://lnkd.in/dYS32dvM
Top comments (0)