liweiphys/layra
LAYRA—an enterprise-ready, out-of-the-box solution—unlocks next-generation intelligent systems powered by visual RAG and limitless visual multi-step agent workflow orchestration.
Builds on FastAPI with async integrations (Redis, MySQL, MongoDB, Kafka, MinIO) and uses ColQwen 2.5 or Jina-Embeddings-v4 APIs to convert documents into semantic vectors stored in Milvus. Features a Next.js 15 frontend, decoupled microservice architecture with independent container deployment, and a Python-native workflow engine supporting cyclic logic, human-in-the-loop checkpoints, and full arbitrary code execution within sandboxed environments.
898 stars.
Stars
898
Forks
99
Language
TypeScript
License
Apache-2.0
Category
Last pushed
Oct 14, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/liweiphys/layra"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
RapidAI/RapidRAG
QA based on local knowledge and LLM.
benitomartin/substack-newsletters-search-course
Production RAG System Course
LHRLAB/HyperGraphRAG
[NeurIPS 2025] Official resources of "HyperGraphRAG: Retrieval-Augmented Generation via...
limanmys/sef
On premise enterprise-grade RAG-powered agentic workflow chatbot platform with multi-provider support
Da1yuqin/EviNoteRAG
Welcome! 😊 This is the official code release of EviNote-RAG, and we’re happy to share it with...