agenticx 0.2.7

A unified, scalable, production-ready multi-agent application development framework

AgenticX: Unified Multi-Agent Framework

Features • Quick Start • Examples • Architecture • Progress

---

Language / 语言: English | 中文

---

Vision

AgenticX aims to create a unified, scalable, production-ready multi-agent application development framework, empowering developers to build everything from simple automation assistants to complex collaborative intelligent agent systems.

Core Features

Core Framework (Completed)

• Agent Core: Agent execution engine based on 12-Factor Agents methodology
• Orchestration Engine: Graph-based orchestration engine supporting complex workflows, conditional routing, and parallel execution
• Tool System: Unified tool interface supporting function decorators, remote tools (MCP), and built-in toolsets
• Memory System: Deep integration with Mem0 for long-term memory, supporting arbitrary LLM models
• Communication Protocol: A2A inter-agent communication, MCP resource access protocol
• Task Validation: Pydantic-based output parsing and auto-repair
• GUI Agent / Embodiment: Complete GUI automation framework with action reflection, stuck detection, action caching, REACT parsing, device-cloud routing, and DAG task verification

Enterprise-Grade Monitoring (Completed)

• Observability: Complete callback system, real-time monitoring, trajectory analysis
• Performance Monitoring: Real-time metrics collection, Prometheus integration, system monitoring
• Trajectory Analysis: Execution path tracing, failure analysis, performance bottleneck identification
• Data Export: Multi-format export (JSON/CSV/Prometheus), time series analysis

Developer Experience (Planned)

• CLI Tools: Command-line tools for project creation, deployment, and monitoring
• Web UI: Visual agent management and monitoring interface
• IDE Integration: VS Code extension, Jupyter kernel support

Enterprise Security (Planned)

• Security Sandbox: Secure code execution environment and resource isolation
• Multi-tenancy: RBAC permission control, data isolation
• Human Approval: Human-in-the-loop workflows, risk control

Quick Start

Installation

Option 1: Install from PyPI (Recommended)

# Core install (lightweight, no torch, installs in seconds)
pip install agenticx

# Install optional features as needed
pip install "agenticx[memory]"      # Memory: mem0, chromadb, qdrant, redis, milvus
pip install "agenticx[document]"    # Document processing: PDF, Word, PPT parsing
pip install "agenticx[graph]"       # Knowledge graph: networkx, neo4j, community detection
pip install "agenticx[llm]"         # Extra LLMs: anthropic, ollama
pip install "agenticx[monitoring]"  # Observability: prometheus, opentelemetry
pip install "agenticx[mcp]"         # MCP protocol
pip install "agenticx[database]"    # Database backends: postgres, SQLAlchemy
pip install "agenticx[data]"        # Data analysis: pandas, scikit-learn, matplotlib
pip install "agenticx[ocr]"         # OCR (pulls in torch ~2GB): easyocr
pip install "agenticx[volcengine]"  # Volcengine AgentKit
pip install "agenticx[all]"         # Everything

Tip: The core package includes only ~27 lightweight dependencies and installs in seconds. Heavy dependencies (torch, pandas, etc.) are optional extras - install only what you need.

Option 2: Install from Source (Development)

# Clone repository
git clone https://github.com/DemonDamon/AgenticX.git
cd AgenticX

# Using uv (recommended, 10-100x faster than pip)
pip install uv
uv pip install -e .                  # Core install
uv pip install -e ".[memory,graph]"  # Add optional features
uv pip install -e ".[all]"           # Everything
uv pip install -e ".[dev]"           # Development tools

# Or using pip
pip install -e .
pip install -e ".[all]"

Environment Setup

# Set environment variables
export OPENAI_API_KEY="your-api-key"
export ANTHROPIC_API_KEY="your-api-key"  # Optional

Complete Installation Guide: For system dependencies (antiword, tesseract) and advanced document processing features, see INSTALL.md

Create Your First Agent

from agenticx import Agent, Task, AgentExecutor
from agenticx.llms import OpenAIProvider

# Create agent
agent = Agent(
    id="data-analyst",
    name="Data Analyst",
    role="Data Analysis Expert", 
    goal="Help users analyze and understand data",
    organization_id="my-org"
)

# Create task
task = Task(
    id="analysis-task",
    description="Analyze sales data trends",
    expected_output="Detailed analysis report"
)

# Configure LLM
llm = OpenAIProvider(model="gpt-4")

# Execute task
executor = AgentExecutor(agent=agent, llm=llm)
result = executor.run(task)
print(result)

Tool Usage Example

from agenticx.tools import tool

@tool
def calculate_sum(x: int, y: int) -> int:
    """Calculate the sum of two numbers"""
    return x + y

@tool  
def search_web(query: str) -> str:
    """Search web information"""
    return f"Search results: {query}"

# Agents will automatically invoke these tools

Complete Examples

We provide rich examples demonstrating various framework capabilities:

Agent Core (M5)

Single Agent Example

# Basic agent usage
python examples/m5_agent_demo.py

• Demonstrates basic agent creation and execution
• Tool invocation and error handling
• Event-driven execution flow

Multi-Agent Collaboration

# Multi-agent collaboration example
python examples/m5_multi_agent_demo.py

• Multi-agent collaboration patterns
• Task distribution and result aggregation
• Inter-agent communication

Orchestration & Validation (M6 & M7)

Simple Workflow

# Basic workflow orchestration
python examples/m6_m7_simple_demo.py

• Workflow creation and execution
• Task output parsing and validation
• Conditional routing and error handling

Complex Workflow

# Complex workflow orchestration
python examples/m6_m7_comprehensive_demo.py

• Complex workflow graph structures
• Parallel execution and conditional branching
• Complete lifecycle management

Agent Communication (M8)

A2A Protocol Demo

# Inter-agent communication protocol
python examples/m8_a2a_demo.py

• Agent-to-Agent communication protocol
• Distributed agent systems
• Service discovery and skill invocation

Observability Monitoring (M9)

Complete Monitoring Demo

# Observability module demo
python examples/m9_observability_demo.py

• Real-time performance monitoring
• Execution trajectory analysis
• Failure analysis and recovery recommendations
• Data export and report generation

Memory System

Basic Memory Usage

# Memory system example
python examples/memory_example.py

• Long-term memory storage and retrieval
• Context memory management

Healthcare Scenario

# Healthcare memory scenario
python examples/mem0_healthcare_example.py  

• Medical knowledge memory and application
• Personalized patient information management

Human-in-the-Loop

Human Intervention Flow

# Human-in-the-loop example
python examples/human_in_the_loop_example.py

• Human approval workflows
• Human-machine collaboration patterns
• Risk control mechanisms

Detailed documentation: examples/README_HITL.md

LLM Integration

Chatbot

# LLM chat example
python examples/llm_chat_example.py

• Multi-model support demonstration
• Streaming response handling
• Cost control and monitoring

Security Sandbox

Code Execution Sandbox

# Micro-sandbox example
python examples/microsandbox_example.py

• Secure code execution environment
• Resource limits and isolation

Technical blog: examples/microsandbox_blog.md

GUI Agent / Embodiment (M16)

GUI Automation Agent

# GUI Agent example
python examples/agenticx-for-guiagent/AgenticX-GUIAgent/main.py

• Complete GUI automation framework with human-aligned learning
• Action reflection (A/B/C classification) and stuck detection
• Action caching system for performance optimization
• REACT output parsing and compact action schema
• Device-Cloud routing for intelligent model selection
• DAG-based task verification

Key capabilities:

• Action Reflection: Automatic action result classification (success/wrong_state/no_change)
• Stuck Detection: Continuous failure detection and recovery strategy recommendation
• Action Caching: Trajectory caching with exact and fuzzy matching (up to 9x speedup)
• REACT Parsing: Standardized REACT format output parsing
• Smart Routing: Dynamic device-cloud model selection based on task complexity and sensitivity
• DAG Verification: Multi-path task verification with dual-semantic dependencies

See: examples/agenticx-for-guiagent/

Technical Architecture

graph TD
    subgraph "User Interface Layer"
        SDK[Python SDK]
        CLI[CLI Tools]
        UI[Web UI]
    end

    subgraph "Core Framework Layer"
        subgraph "Orchestration Engine"
            Orchestrator[Workflow Orchestrator]
        end
        subgraph "Execution Engine"
            AgentExecutor[Agent Executor]
            TaskValidator[Task Validator]
        end
        subgraph "Core Components"
            Agent[Agent]
            Task[Task]
            Tool[Tool]
            Memory[Memory]
            LLM[LLM Provider]
        end
    end

    subgraph "Platform Services Layer"
        subgraph "Observability"
            Monitoring[Monitoring System]
        end
        subgraph "Communication Protocols"
            Protocols[Protocol Handler]
        end
        subgraph "Security Governance"
            Security[Security Service]
        end
    end

    SDK --> Orchestrator
    Orchestrator --> AgentExecutor
    AgentExecutor --> Agent
    Agent --> Tool
    Agent --> Memory
    Agent --> LLM
    AgentExecutor --> Monitoring
    Agent --> Protocols

Development Progress

✅ Completed Modules (M1-M9, M16)

Module	Status	Description
M1	✅	Core Abstraction Layer - Basic data structures like Agent, Task, Tool, Workflow
M2	✅	LLM Service Layer - Unified LLM interface based on LiteLLM, supporting 100+ models
M3	✅	Tool System - Function decorators, MCP remote tools, built-in toolsets
M4	✅	Memory System - Deep integration with Mem0, supporting custom LLM
M5	✅	Agent Core - Complete think-act loop, event-driven architecture
M6	✅	Task Validation - Pydantic-based output parsing and auto-repair
M7	✅	Orchestration Engine - Graph-based workflows, conditional routing, parallel execution
M8	✅	Communication Protocols - A2A agent communication, MCP resource access
M9	✅	Observability - Complete monitoring, trajectory analysis, performance metrics
M16	✅	Embodiment Module - GUI Agent framework with action reflection, stuck detection, action caching, REACT output parsing, device-cloud routing, and DAG task verification

Planned Modules (M10-M13)

Module	Status	Description
M10	🚧	Developer Experience - CLI, Web UI, IDE integration
M11	🚧	Enterprise Security - Multi-tenancy, RBAC, security sandbox
M12	🚧	Agent Evolution - Architecture search, knowledge distillation
M13	🚧	Knowledge Hub - Enterprise data connection, unified search

Core Advantages

• Unified Abstraction: Clear and consistent core abstractions, avoiding conceptual confusion
• Pluggable Architecture: All components are replaceable, avoiding vendor lock-in
• Enterprise-Grade Monitoring: Complete observability, production-ready
• Security First: Built-in security mechanisms and multi-tenant support
• High Performance: Optimized execution engine and concurrent processing
• Rich Ecosystem: Complete toolset and example library

System Requirements

• Python: 3.10+
• Memory: 4GB+ RAM recommended
• System: Windows / Linux / macOS
• Core Dependencies: ~27 lightweight packages, installs in seconds (see pyproject.toml)
• Optional Dependencies: 15 feature groups available via pip install "agenticx[xxx]"

Contributing

We welcome community contributions! Please refer to:

1. Submit Issues to report bugs or request features
2. Fork the project and create feature branches
3. Submit Pull Requests, ensuring all tests pass
4. Participate in code reviews and discussions

License

This project is licensed under the GNU Affero General Public License v3.0 (AGPL-3.0) - see LICENSE file for details

Star History

---

If AgenticX helps you, please give us a Star!

GitHub • Documentation • Examples • Discussions