better-cheaper-llm
davidzna/better-cheaper-llm
Use Jev instead of an LLM for RAG decisions: relevance grading, query routing, hallucination checks and LLM-as-a-judge evals. Faster, cheaper, measured first.
Python
- Stars
- 0
- Forks
- 0
Why it is listed
Audits existing LLM logs for decision calls, replays them with Jev and offers shadow/enforce checks with LLM fallback; migration is preceded by traffic-specific measurement.