# ModelEngine-Group/app-platform

AppPlatform 是一个前沿的大模型应用工程，旨在通过集成的声明式编程和低代码配置工具，简化和优化大模型的训练与推理应用的开发过程。本工程为软件工程师和产品经理提供一个强大的、可扩展的环境，以支持从概念到部署的全流程 AI 应用开发。

Repository: https://github.com/ModelEngine-Group/app-platform
Canonical: https://ross.abutalabs.com/products/app-platform
Homepage: https://modelengine-ai.net
Language: Java
License: MIT
License Family: permissive
Topics: ai, java, low-code, agent, agentic-ai, agentic-workflow
Last push: 2026-08-26T07:29:39+00:00

## Health v2 (maintenance only)
Score: 76/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 68, longevity 37
- inputs: {"age_days": 520, "days_push": 7, "days_rel": 216, "gap_med": 19, "n_releases_24m": 14}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1455, forks 233 (observed 2026-08-28T04:04:46.804232+00:00)

## What it is
AppPlatform is a self-hosted low-code platform for building, orchestrating, debugging, and deploying large language model applications such as agents, RAG pipelines, and AI tools. It combines a Java/FIT plugin-based backend with a React visual flow editor (Elsa graph engine) and supports multi-model orchestration via Docker Compose deployment.

## Use cases
- build ai agent apps without writing code
- visually orchestrate llm workflows
- create rag applications with a low-code editor
- self-host an ai application builder platform
- combine multiple llm models in one workflow
- let product managers prototype ai apps
- develop custom plugin nodes for ai pipelines
- publish and share reusable ai tools in an app store

## When to choose
- you want a self-hosted, open-source alternative for visual LLM app building
- your team is Java-centric and wants plugin-based AI app development
- non-developers need to build AI applications through a graphical interface
- you need multi-model orchestration and reusable tool/app stores

## When to avoid
- you need a lightweight SDK or library to embed in an existing app rather than a full platform
- you require a fully managed cloud service with no self-hosting overhead
- your stack is Python-only and you prefer Python-native agent frameworks

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, rag, workflow-automation, llm-inference, plugin-system, chatbot
- domain: artificial-intelligence, large-language-models, developer-tools, self-hosted
- platform: self-hosted, jvm, python
- tags: low-code, visual-workflow-orchestration, declarative-programming, agentic-workflow, ai-app-builder, java, react, fit-framework, waterflow, elsa-graph-engine, app-store, smart-forms, ai-agents, retrieval-augmented-generation, docker, web-server

## Member repositories
- ModelEngine-Group/app-platform (main) score 76

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:46.804232+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:35:37.886674+00:00, confidence not recorded.
  - readme: https://github.com/ModelEngine-Group/app-platform (fetched 2026-08-28T04:04:46.804232+00:00, sha 969be7511174)
- Data as of 2026-08-30T08:39:29.467469+00:00.