ENDEVSOLS/LongTracer

Detect hallucinations in LLM responses. Verify every claim against source documents using hybrid STS + NLI. Works with LangChain, LlamaIndex, or any RAG pipeline. pip install longtracer

42
/ 100
Emerging

This tool helps developers and AI engineers ensure the reliability of responses generated by Large Language Models (LLMs) in applications like chatbots or knowledge retrieval systems. It takes an LLM's response and a set of source documents, then verifies each claim made in the response against those sources. The output is a clear verdict on whether the response contains factual errors or 'hallucinations', along with a trust score and details on conflicting statements.

Available on PyPI.

Use this if you are building an LLM application and need to automatically detect and prevent incorrect or fabricated information in the model's output by cross-referencing it with provided source materials.

Not ideal if you need to evaluate the LLM's creativity, coherence, or style, as this tool focuses strictly on factual accuracy against provided sources.

LLM application development AI quality assurance Generative AI evaluation RAG pipeline monitoring Fact-checking
Maintenance 13 / 25
Adoption 5 / 25
Maturity 18 / 25
Community 6 / 25

How are scores calculated?

Stars

12

Forks

1

Language

Python

License

MIT

Category

pipeline

Last pushed

Apr 03, 2026

Commits (30d)

0

Dependencies

5

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/ENDEVSOLS/LongTracer"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.