2501Pr0ject/RAGnarok-AI

Local-first RAG evaluation framework for LLM applications. 100% local, no API keys required.

50
/ 100
Established

Supports LangChain, LangGraph, LlamaIndex, and custom RAG pipelines with built-in checkpointing for resumable evaluations. Uses local LLM-as-Judge scoring (faithfulness, relevance, hallucination) with Prometheus metrics and Ollama integration, achieving ~24K retrieval queries/sec while maintaining minimal dependencies. Includes CLI-first design, CI/CD GitHub Actions, and Kubernetes deployment support for production monitoring and cost tracking.

Available on PyPI.

Maintenance 10 / 25
Adoption 11 / 25
Maturity 18 / 25
Community 11 / 25

How are scores calculated?

Stars

13

Forks

2

Language

Python

License

AGPL-3.0

Last pushed

Feb 28, 2026

Monthly downloads

308

Commits (30d)

0

Dependencies

3

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/2501Pr0ject/RAGnarok-AI"

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