msu-denver/bili-core

bili-core is an open-source framework for LLM benchmarking using LangChain, LangGraph, Streamlit, and Flask. It enables effective LLM model comparisons, Retrieval-Augmented Generation (RAG), and customizable decision workflows. Part of MSU Denver’s Sustainability Hub, bili-core promotes data democracy and transparent, reproducible AI research. 🚀

39
/ 100
Emerging

This tool helps researchers and AI practitioners compare the performance of different Large Language Models (LLMs) and fine-tune how they retrieve information (RAG). You input various LLMs, custom prompts, and external tools, then receive benchmark results and a customized RAG implementation. Anyone who needs to rigorously test and optimize LLM applications for specific tasks will find this valuable.

Use this if you need to systematically evaluate different LLMs, customize how they find and use information, and build complex conversational agents without running models locally.

Not ideal if you're looking for a simple, pre-configured chatbot solution without any need for benchmarking or deep customization of RAG parameters.

AI-research LLM-evaluation conversational-AI-development AI-benchmarking natural-language-processing
No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

9

Forks

1

Language

Python

License

MIT

Last pushed

Mar 13, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/msu-denver/bili-core"

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