# ageerle/ruoyi-ai

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/ageerle-ruoyi-ai).**

4,788 stars · 1,182 forks · Java · mit

## Links

- GitHub: https://github.com/ageerle/ruoyi-ai
- Homepage: http://doc.pandarobot.chat
- awesome-repositories: https://awesome-repositories.com/repository/ageerle-ruoyi-ai.md

## Topics

`agent` `ai` `knowledge` `mcp` `rag`

## Description

Ruoyi AI is a multi-agent orchestration platform that coordinates specialized AI agents through a supervisor-based delegation pattern, allowing complex requests to be broken into subtasks that are assigned, executed, and merged under centralized control. It provides a unified abstraction layer that connects multiple AI model providers behind a single interface, so switching between providers requires no application code changes. The platform also includes a retrieval-augmented generation engine that indexes internal documents into vector stores and retrieves relevant context at query time to ground generative responses in proprietary data.

What distinguishes the platform is its combination of visual workflow design and structured tool-calling in a single system. A drag-and-drop canvas lets operators construct multi-step AI pipelines from components and execute them with real-time streaming output, while a typed tool-calling protocol defines how agents invoke external functions with parameter validation and result parsing. The platform also provides a framework for defining custom tools that agents can call when interacting with external systems and data sources.

Supporting capabilities include building and querying knowledge bases, integrating third-party AI platforms, and automating workflows that chain tool calls, agents, and conditional logic into repeatable sequences.

## Tags

### Artificial Intelligence & ML

- [Multi-Agent Orchestration Platforms](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/coordination-and-routing/multi-agent-orchestration-platforms.md) — Coordinates multiple AI agents, integrates model providers, and executes multi-step workflows.
- [Agent Workflow Orchestrations](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-workflow-orchestrations.md) — Defines and executes sequences of AI agent tasks that collaborate to complete processes, routing subtasks and merging results. ([source](https://doc.pandarobot.chat/))
- [Agentic Task Orchestrators](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-task-orchestrators.md) — Decomposes complex requests into subtasks managed by a supervisor agent that delegates and coordinates specialized sub-agents.
- [AI Model Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-model-integrations.md) — Integrates with multiple AI model providers and third-party platforms through a unified interface. ([source](https://cdn.jsdelivr.net/gh/ageerle/ruoyi-ai@main/README.md))
- [AI Tooling Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-tooling-frameworks.md) — Ships a typed framework for defining executable tools that AI agents call to interact with external systems.
- [AI Workflow Builders](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-workflow-builders.md) — Provides a drag-and-drop interface for designing multi-step AI workflows with tool calls and conditional logic.
- [Retrieval-Augmented Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/conversational-interfaces/retrieval-augmented-generation.md) — Supplements generative outputs with relevant external knowledge retrieved from vector stores or documents. ([source](https://doc.pandarobot.chat))
- [Model Provider Abstractions](https://awesome-repositories.com/f/artificial-intelligence-ml/model-provider-abstractions.md) — Abstracts multiple AI provider SDKs behind a common interface, enabling seamless provider switching without changing application code.
- [Multi-Agent Orchestrators](https://awesome-repositories.com/f/artificial-intelligence-ml/multi-agent-orchestrators.md) — Orchestrates specialized AI agents with a supervisor pattern to solve complex tasks together. ([source](https://cdn.jsdelivr.net/gh/ageerle/ruoyi-ai@main/README.md))
- [Multi-Model AI Interfaces](https://awesome-repositories.com/f/artificial-intelligence-ml/multi-model-ai-interfaces.md) — Provides a unified abstraction layer for switching between multiple AI model providers without code changes.
- [Provider-Agnostic Model Interfaces](https://awesome-repositories.com/f/artificial-intelligence-ml/provider-agnostic-model-interfaces.md) — Abstracts multiple AI providers behind a unified interface, allowing seamless model swapping and third-party platform connectivity.
- [Retrieval Augmented Generation Pipelines](https://awesome-repositories.com/f/artificial-intelligence-ml/retrieval-augmented-generation-pipelines.md) — Indexes documents into vector stores and retrieves relevant context at query time to ground generative responses in proprietary data.
- [Supervisor Agent Configurations](https://awesome-repositories.com/f/artificial-intelligence-ml/supervisor-agent-configurations.md) — Coordinates specialized sub-agents through a central supervisor that delegates tasks and merges results for complex collaborative workflows.
- [Visual AI Workflow Builders](https://awesome-repositories.com/f/artificial-intelligence-ml/visual-ai-workflow-builders.md) — Ships a drag-and-drop canvas for constructing multi-step AI pipelines executed with real-time streaming output.
- [Knowledge Base Retrieval](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-rag-development/knowledge-base-retrieval.md) — Parses documents, stores embeddings in a vector database, and retrieves relevant context for AI responses. ([source](https://cdn.jsdelivr.net/gh/ageerle/ruoyi-ai@main/README.md))
- [Retrieval Augmented Generation Engines](https://awesome-repositories.com/f/artificial-intelligence-ml/retrieval-augmented-generation-engines.md) — Indexes internal documents and retrieves relevant context to ground AI responses in proprietary data.
- [Multi-Type Step Chains](https://awesome-repositories.com/f/artificial-intelligence-ml/step-based-schedulers/step-execution-engines/multi-type-step-chains.md) — Defines and executes multi-step workflows that chain tool calls, agents, and conditional logic. ([source](https://doc.pandarobot.chat))
- [Tool-Calling Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/tool-calling-frameworks.md) — Defines a typed interface for agent-invoked external functions, handling parameter validation and result parsing within a unified call framework.
- [Tool-Calling Interfaces](https://awesome-repositories.com/f/artificial-intelligence-ml/tool-calling-interfaces.md) — Defines executable tools that agents can invoke to interact with external systems via a structured function-calling protocol.

### Part of an Awesome List

- [Custom Tool Exposures](https://awesome-repositories.com/f/awesome-lists/ai/ai-and-data-tools/custom-tool-exposures.md) — Creates custom tools for AI agents to invoke when interacting with external systems. ([source](https://cdn.jsdelivr.net/gh/ageerle/ruoyi-ai@main/README.md))

### Development Tools & Productivity

- [Custom Tool Definitions](https://awesome-repositories.com/f/development-tools-productivity/ai-agent-development-tools/custom-tool-definitions.md) — Provides a typed protocol for defining executable tools that AI agents invoke to interact with external systems.
- [Visual Workflow Engines](https://awesome-repositories.com/f/development-tools-productivity/visual-workflow-engines.md) — Provides a drag-and-drop canvas for constructing multi-step AI pipelines, converting visual diagrams into executable step sequences.
- [AI Workflow Designers](https://awesome-repositories.com/f/development-tools-productivity/workflow-automation-triggers/ai-workflow-designers.md) — Provides a drag-and-drop canvas for constructing multi-step AI pipelines, then executes them with real-time streaming output.