Run This Ai
EN DE

Bisheng

Open-source LLM DevOps platform for enterprise AI applications with GenAI workflow, RAG, Agent, model management, evaluation, SFT, and dataset management

★ 11,495 GitHub Apache-2.0 llmragagentworkflowllmopsdevopsenterprise Automation Tools

Overview

Bisheng is an open-source LLM DevOps platform built for next-generation enterprise AI applications. It provides a comprehensive suite of tools including GenAI workflow orchestration, Retrieval-Augmented Generation (RAG), AI Agents, unified model management across multiple LLM providers, model evaluation and fine-tuning (SFT), and dataset management. With over 11,000 GitHub stars and 200K+ Docker pulls, Bisheng enables organizations to build, deploy, and monitor production-grade AI applications. The platform features a visual workflow builder for creating complex AI pipelines without coding, support for local and cloud-based LLMs (including OpenAI, Llama, Qwen, and more), built-in document parsing with OCR capabilities, and enterprise-grade security features. Bisheng is built with Python and TypeScript, offering both REST API and Web UI interfaces. Its modular architecture allows teams to start with simple RAG chatbots and scale up to sophisticated multi-agent systems with human-in-the-loop approval workflows.

Requirements

Min vCPU
2
Min RAM
4096 MB
Min Disk
10 GB
Rec vCPU
4
Rec RAM
16384 MB
Rec Disk
20 GB

Recommended VPS

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Hostinger · KVM 8

8 vCPU · 32256 MB · 400 GB

$20.00
View plan

Affiliate disclosure

Docker Compose

# Generated by Run This Ai — docker-compose.yml
services:
  bisheng:
    image: dataelement/bisheng-backend:latest
    restart: unless-stopped
    ports:
      - 8080:8080
    volumes:
      - ./data/bisheng:/data

Best VPS for Bisheng →

Related tools

Guides & articles