cool-japan/oxirag
A four-layer Retrieval-Augmented Generation (RAG) engine in Rust with SMT-based logic verification and knowledge graph support.
This project helps generate highly reliable answers from your documents by first searching for relevant information and then carefully verifying the logical consistency of the generated response. It takes natural language queries and a collection of text documents as input, then outputs a confidence-scored answer. This tool is ideal for developers and engineers building applications that require accurate, verifiable answers from potentially complex data sources.
Use this if you are building an application that needs to answer questions based on a body of text, and the correctness and logical consistency of those answers are critical.
Not ideal if you need a simple, off-the-shelf chatbot or a solution for highly subjective, creative text generation tasks.
Stars
8
Forks
1
Language
Rust
License
Apache-2.0
Category
Last pushed
Feb 07, 2026
Monthly downloads
541
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/cool-japan/oxirag"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
raphaelmansuy/edgequake
High-performance GraphRAG inspired from LightRag written in Rust
bosun-ai/swiftide
Fast, streaming indexing, query, and agentic LLM applications in Rust
AlphaCorp-AI/RustyRAG
⚡ Sub-200ms RAG API built in Rust — document ingestion, Milvus vector search, Jina AI local...
kkollsga/kglite
Lightweight in-memory knowledge graph with Cypher query support
pixlie/PixlieAI
Please check our new project with similar targets: https://github.com/pixlie/Pixlie