onestardao/WFGY
WFGY: open-source reasoning and debugging infrastructure for RAG and AI agents. Includes the 16-problem RAG failure map, Global Debug Card, and the WFGY 3.0 TXT stress-test engine. ⭐ Star if you care about reliable reasoning and system-level alignment.
This project offers an open-source framework for building and managing 'language selves' or AI avatars, which are dynamic, reusable AI entities. It helps users define and control their AI's behavior across different interactions and tasks. The target users are AI system developers or engineers responsible for creating and maintaining reliable AI agents and RAG pipelines.
1,620 stars. Actively maintained with 551 commits in the last 30 days.
Use this if you are developing or managing AI agents or RAG systems and need robust tools to diagnose, debug, and govern their reasoning and behavior.
Not ideal if you are looking for a simple, plug-and-play AI writing tool or a basic prompt collection, as this is a deeper infrastructure project.
Stars
1,620
Forks
146
Language
Jupyter Notebook
License
—
Category
Last pushed
Mar 13, 2026
Commits (30d)
551
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/onestardao/WFGY"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
KRLabsOrg/verbatim-rag
Hallucination-prevention RAG system with verbatim span extraction. Ensures all generated content...
iMoonLab/Hyper-RAG
"Hyper-RAG: Combating LLM Hallucinations using Hypergraph-Driven Retrieval-Augmented Generation"...
frmoretto/clarity-gate
Stop LLMs from hallucinating your guesses as facts. Clarity Gate is a verification protocol for...
project-miracl/nomiracl
NoMIRACL: A multilingual hallucination evaluation dataset to evaluate LLM robustness in RAG...
chensyCN/LogicRAG
Source code of LogicRAG at AAAI'26.