Skip to content

Add VeroQ - production LLM output verification#727

Open
JohnnyTarrr wants to merge 1 commit intoEthicalML:masterfrom
JohnnyTarrr:add-veroq
Open

Add VeroQ - production LLM output verification#727
JohnnyTarrr wants to merge 1 commit intoEthicalML:masterfrom
JohnnyTarrr:add-veroq

Conversation

@JohnnyTarrr
Copy link
Copy Markdown

What is VeroQ?

VeroQ Shield verifies any LLM output in one function call:

from veroq import shield
result = shield("NVIDIA reported $22B in Q4 revenue")
print(result.trust_score)   # 0.73
print(result.corrections)   # [{claim, correction}]
  • Extracts claims from any LLM text
  • Verifies each against live evidence (web search, financial data, public records)
  • Returns trust score, corrections, and permanent verification receipts
  • Python (pip install veroq) and TypeScript (npm install @veroq/sdk)
  • 2,000+ weekly installs across npm and PyPI

Placement

Added under Evaluation and Monitoring in alphabetical order (between TrustLLM and VBench). VeroQ is a production-grade tool for verifying LLM outputs in real time — it fits alongside the other evaluation and monitoring tools in this section.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant