CrestingRadarGet featured →

Rank #752 · on radar since 2026-07-03

Veridoc

A fully local, privacy-preserving RAG pipeline optimized for reasoning over dense financial documents. Veridoc uses LLMLingua-2 for token-level context compression and local LLMs to solve the "lost in the middle" problem—enabling multi-hop reasoning on SEC filings without external cloud APIs.

Visit homepage ↗llmrag-chatbotoptimisationaiml+3GitHub

Momentum

42.2
24h7d

Why it's ranked

Every score decomposes into published factors — the same math for every tool, paid or not. Read the methodology →

Velocity (weighted, cohort-normalized)0.438
Signal decay0.995
Corroboration1.000
Quality gate1.000

Raw signals (30 days)

github · forks0 latest · 2 snapshots
github · stars1 latest · 2 snapshots