corefrg/lexicont

Lightweight LLM agent for text moderation with deterministic pipeline: profanity rules → ML → LLM. Production-grade, YAML configurable. Uses glin-profanity + rapidfuzz + detoxify with Qwen LLM agent (llamacpp/Ollama) + RAG. Early-stop logic. Pure Python, CLI/API/SDK.

24
/ 100
Experimental
No Package No Dependents
Maintenance 13 / 25
Adoption 0 / 25
Maturity 11 / 25
Community 0 / 25

How are scores calculated?

Stars

—

Forks

—

Language

Python

License

MIT

Category

pipeline

Last pushed

Apr 04, 2026

Commits (30d)

0

GitHub
Pipeline · 126 tools

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/corefrg/lexicont"

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

Higher-rated alternatives

DemonDamon/AgenticX

AgenticX is a unified, production-ready multi-agent platform — Python SDK + CLI (agx) + Studio...

62

ai-deeptech/stratarouter

Production-grade semantic routing for AI systems. Fast Rust core. Hybrid scoring. 9 framework...

43

ENDEVSOLS/LongTracer

Detect hallucinations in LLM responses. Verify every claim against source documents using hybrid...

42

hoangtung386/Medical_RAG_PJI

Backend AI ho tro quyet dinh lam sang Nhiem trung Khop gia (PJI) — RAG pipeline voi Llama 4,...

35

tdiprima/langchain-lab

Runnable Python examples for LangChain, LangGraph, and LangSmith — agents, RAG, memory, and...

30

Explore RAG Tools

All categories Trending RAG directory Insights