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.

48
/ 100
Emerging

LAYRA is a powerful AI automation engine that understands documents visually, just like a human. It takes various document types as input and outputs structured information or automated actions, preserving layout and graphical details. This tool is ideal for enterprise users such as business analysts, operations managers, or data scientists who need to extract complex information from documents and automate multi-step processes.

898 stars. No commits in the last 6 months.

Use this if you need to build advanced AI agents that can 'see' and understand visual documents, automate complex workflows with multiple steps and human intervention, and handle both text and image data.

Not ideal if your primary need is simple text-based retrieval, or if you prefer a system that doesn't involve visual document processing or complex multi-step agent orchestrations.

document-intelligence business-process-automation visual-data-extraction AI-workflow-orchestration enterprise-automation
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

898

Forks

99

Language

TypeScript

License

Apache-2.0

Category

rag-applications

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.