AIGNE-io
/
aigne-framework
star
22
AIGNE Framework
Visit Github

English | 中文

GitHub star chart Open Issues codecov NPM Version MIT licensed

What is AIGNE Framework

AIGNE Framework is a functional AI application development framework designed to simplify and accelerate the process of building modern applications. It combines functional programming features, powerful artificial intelligence capabilities, and modular design principles to help developers easily create scalable solutions. AIGNE Framework is also deeply integrated with the Blocklet ecosystem, providing developers with a wealth of tools and resources.

Key Features

  • Modular Design: With a clear modular structure, developers can easily organize code, improve development efficiency, and simplify maintenance.
  • TypeScript Support: Comprehensive TypeScript type definitions are provided, ensuring type safety and enhancing the developer experience.
  • Blocklet Ecosystem Integration: Closely integrated with the Blocklet ecosystem, providing developers with a one-stop solution for development and deployment.

Usage

import { AIAgent, ExecutionEngine } from "@aigne/core";
import { OpenAIChatModel } from "@aigne/core/models/openai-chat-model.js";
import { DEFAULT_CHAT_MODEL, OPENAI_API_KEY } from "../env";

const model = new OpenAIChatModel({
  apiKey: OPENAI_API_KEY,
  model: DEFAULT_CHAT_MODEL,
});

function transferToAgentB() {
  return agentB;
}

function transferToAgentA() {
  return agentA;
}

const agentA = AIAgent.from({
  name: "AgentA",
  instructions: "You are a helpful agent.",
  outputKey: "A",
  tools: [transferToAgentB],
});

const agentB = AIAgent.from({
  name: "AgentB",
  instructions: "Only speak in Haikus.",
  outputKey: "B",
  tools: [transferToAgentA],
});

const engine = new ExecutionEngine({ model });

const userAgent = await engine.call(agentA);

const response = await userAgent.call("transfer to agent b");
// output
// {
//   B: "Agent B awaits here,  \nIn haikus I shall speak now,  \nWhat do you seek, friend?",
// }

Packages

  • examples - Example project demonstrating how to use different agents to handle various tasks.
  • packages/core - Core package providing the foundation for building AIGNE applications.

Documentation

Architecture

AIGNE Framework supports various workflow patterns to address different AI application needs:

Sequential Workflow

flowchart LR
in(In)
out(Out)
conceptExtractor(Concept Extractor)
writer(Writer)
formatProof(Format Proof)

in --> conceptExtractor --> writer --> formatProof --> out

classDef inputOutput fill:#f9f0ed,stroke:#debbae,stroke-width:2px,color:#b35b39,font-weight:bolder;
classDef processing fill:#F0F4EB,stroke:#C2D7A7,stroke-width:2px,color:#6B8F3C,font-weight:bolder;

class in inputOutput
class out inputOutput
class conceptExtractor processing
class writer processing
class formatProof processing

Concurrency Workflow

flowchart LR
in(In)
out(Out)
featureExtractor(Feature Extractor)
audienceAnalyzer(Audience Analyzer)
aggregator(Aggregator)

in --> featureExtractor --> aggregator
in --> audienceAnalyzer --> aggregator
aggregator --> out

classDef inputOutput fill:#f9f0ed,stroke:#debbae,stroke-width:2px,color:#b35b39,font-weight:bolder;
classDef processing fill:#F0F4EB,stroke:#C2D7A7,stroke-width:2px,color:#6B8F3C,font-weight:bolder;

class in inputOutput
class out inputOutput
class featureExtractor processing
class audienceAnalyzer processing
class aggregator processing

Router Workflow

flowchart LR
in(In)
out(Out)
triage(Triage)
productSupport(Product Support)
feedback(Feedback)
other(Other)

in ==> triage
triage ==> productSupport ==> out
triage -.-> feedback -.-> out
triage -.-> other -.-> out

classDef inputOutput fill:#f9f0ed,stroke:#debbae,stroke-width:2px,color:#b35b39,font-weight:bolder;
classDef processing fill:#F0F4EB,stroke:#C2D7A7,stroke-width:2px,color:#6B8F3C,font-weight:bolder;

class in inputOutput
class out inputOutput
class triage processing
class productSupport processing
class feedback processing
class other processing

Handoff Workflow

flowchart LR

in(In)
out(Out)
agentA(Agent A)
agentB(Agent B)

in --> agentA --transfer to b--> agentB --> out

classDef inputOutput fill:#f9f0ed,stroke:#debbae,stroke-width:2px,color:#b35b39,font-weight:bolder;
classDef processing fill:#F0F4EB,stroke:#C2D7A7,stroke-width:2px,color:#6B8F3C,font-weight:bolder;

class in inputOutput
class out inputOutput
class agentA processing
class agentB processing

Reflection Workflow

flowchart LR
in(In)
out(Out)
coder(Coder)
reviewer(Reviewer)

in --Ideas--> coder ==Solution==> reviewer --Approved--> out
reviewer ==Rejected==> coder

classDef inputOutput fill:#f9f0ed,stroke:#debbae,stroke-width:2px,color:#b35b39,font-weight:bolder;
classDef processing fill:#F0F4EB,stroke:#C2D7A7,stroke-width:2px,color:#6B8F3C,font-weight:bolder;

class in inputOutput
class out inputOutput
class coder processing
class reviewer processing

Code Execution Workflow

flowchart LR

in(In)
out(Out)
coder(Coder)
sandbox(Sandbox)

coder -.-> sandbox
sandbox -.-> coder
in ==> coder ==> out


classDef inputOutput fill:#f9f0ed,stroke:#debbae,stroke-width:2px,color:#b35b39,font-weight:bolder;
classDef processing fill:#F0F4EB,stroke:#C2D7A7,stroke-width:2px,color:#6B8F3C,font-weight:bolder;

class in inputOutput
class out inputOutput
class coder processing
class sandbox processing

Examples

MCP Server Integration

  • Puppeteer MCP Server - Learn how to leverage Puppeteer for automated web scraping through the AIGNE Framework.
  • SQLite MCP Server - Explore database operations by connecting to SQLite through the Model Context Protocol.
  • Github - Interact with GitHub repositories using the GitHub MCP Server.

Workflow Patterns

  • Workflow Router - Implement intelligent routing logic to direct requests to appropriate handlers based on content.
  • Workflow Sequential - Build step-by-step processing pipelines with guaranteed execution order.
  • Workflow Concurrency - Optimize performance by processing multiple tasks simultaneously with parallel execution.
  • Workflow Handoff - Create seamless transitions between specialized agents to solve complex problems.
  • Workflow Reflection - Enable self-improvement through output evaluation and refinement capabilities.
  • Workflow Orchestration - Coordinate multiple agents working together in sophisticated processing pipelines.
  • Workflow Code Execution - Safely execute dynamically generated code within AI-driven workflows.
  • Workflow Group Chat - Share messages and interact with multiple agents in a group chat environment.

Contributing and Releasing

AIGNE Framework uses release-please for version management and release automation. For details on the release process and contributing guidelines, please see RELEASING.md and CONTRIBUTING.md.

Community and Support

AIGNE Framework has a vibrant developer community offering various support channels:

  • Documentation Center: Comprehensive official documentation to help developers get started quickly.
  • Technical Forum: Exchange experiences with global developers and solve technical problems.
Stars
22
Mar 13Mar 18Mar 24Mar 30Apr 05Apr 11
mcpradar.com © 2024 - 2025.
Made by @bytesbay
ExploreAPI