Search

More Filters

Show More
Add Listing
Go Back

layra

0
New
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

LAYRA is an open source, enterprise-grade AI agent engine designed to build visual-native agents and orchestrate complex workflows that see, understand, and act on documents and multimodal content. The repository provides a complete stack including a Next.js frontend, a FastAPI backend, and containerized services for Redis, MySQL, MongoDB, Kafka, MinIO and Milvus. It focuses on visual-first Retrieval-Augmented Generation by embedding full pages with ColQwen or Jina embeddings to preserve layout, tables, figures and other visual elements. The project enables developers and operators to deploy a scalable, debuggable platform via Docker Compose with options for local GPU model deployment or cloud embedding APIs. It includes tooling for document upload and indexing, event-driven asynchronous workflow execution, persistent chat memory, and human-in-the-loop controls to support production-grade agent applications.

Links

Stars
792
App URL
https://github.com/liweiphys/layra
Github Repository
https://github.com/liweiphys/layra/blob/main/README.md

Categorization

App Details

Features
LAYRA combines a visual RAG engine with a workflow orchestration system and developer tooling. Key features include pure visual embeddings that preserve layout and graphics across 100+ formats, support for colqwen2.5 and jina-embeddings-v4, and vector storage in Milvus. The Agent Workflow Engine supports nested loops, conditional branching, arbitrary Python execution in sandboxed runtimes with pip installs, live Server-Sent Events streaming, breakpoint debugging, state snapshots in Redis/MongoDB, and human-in-the-loop approvals. It integrates chat memory and Model Context Protocol (MCP) for live context access. The stack is containerized for scalable deployment and includes observability, AST-based scanner for code vulnerability checks, and import/exportable reusable workflow components. Frontend uses Next.js and Tailwind for a drag-and-drop workflow builder and layout-preserving Q&A UI.
Use Cases
LAYRA helps teams build AI systems that understand documents like humans and automate complex, multi-step processes. By using visual-first embeddings it avoids layout loss common to text-only RAG and provides more accurate answers for PDFs, DOCX, XLSX, PPTX and other formats. The workflow engine enables automation of recursive and conditional tasks with real-time debugging and human approvals, aiding safe production deployment. Sandbox execution and runtime snapshots reduce operational risk while Kafka-driven orchestration and Dockerized services support scalable enterprise installs. The option to use a cloud embedding API lowers GPU barriers for small teams while local ColQwen deployment supports high-performance use with GPUs. The repo includes quick start and deployment guidance for Docker Compose to accelerate trial and production setups.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1009)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (764)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

virtual lab

0 (0 review)
listing image

mnemo

0 (0 review)
listing image

EdgeChains

0 (0 review)
listing image

RAG Agents Accelerator

0 (0 review)
listing image

LLM Zero to Hundred

0 (0 review)

Featured Listings

Tags

Please fill the required fields*