菜单
AgenticX zero-to-hero quickstart guide. Use when the user wants to get started with AgenticX, create their first project, build their first agent, or run their first workflow. Covers installation, project scaffolding, agent creation, task execution, and CLI basics.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/DemonDamon/AgenticX --skill agenticx-quickstart命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Guide for using the A2A (Agent-to-Agent) communication protocol in AgenticX including agent discovery, skill invocation, remote agent cards, and distributed agent systems. Use when the user wants agents to communicate with each other, set up distributed agent systems, invoke remote agent skills, or build agent-to-agent workflows.
Guide for deploying AgenticX agents to production including Docker containerization, Kubernetes orchestration, Volcengine AgentKit cloud deployment, and API server setup. Use when the user wants to deploy agents, containerize applications, set up Kubernetes, configure cloud deployment, or run the AgenticX API server in production.
Guide for setting up and using the AgenticX memory system including Mem0 integration, long-term memory, context management, and memory-enhanced agents. Use when the user wants to add memory to agents, persist conversation history, build memory-aware workflows, or integrate with Mem0 for long-term recall.
基于 SOC 职业分类
正在显示 SKILL.md
| name | agenticx-quickstart |
| description | AgenticX zero-to-hero quickstart guide. Use when the user wants to get started with AgenticX, create their first project, build their first agent, or run their first workflow. Covers installation, project scaffolding, agent creation, task execution, and CLI basics. |
| metadata | {"author":"AgenticX","version":"0.5.0"} |
Guide for getting a user from zero to a running AgenticX agent in under 5 minutes.
# Core install (lightweight, ~27 deps, installs in seconds)
pip install agenticx
# Verify
agx --version
Optional extras — install only what you need:
| Extra | What it adds | Command |
|---|---|---|
memory | Mem0, ChromaDB, Qdrant | pip install "agenticx[memory]" |
document | PDF/PPT/Word parsing | pip install "agenticx[document]" |
server | API server (agx serve) | pip install "agenticx[server]" |
volcengine | Volcengine AgentKit | pip install "agenticx[volcengine]" |
all | Everything | pip install "agenticx[all]" |
export OPENAI_API_KEY="sk-..."
# Optional
export ANTHROPIC_API_KEY="sk-ant-..."
agx project create my-first-agent --template basic
cd my-first-agent
agx project info
from agenticx import Agent, Task, AgentExecutor
from agenticx.llms import OpenAIProvider
agent = Agent(
id="data-analyst",
name="Data Analyst",
role="Data Analysis Expert",
goal="Help users analyze and understand data",
organization_id="my-org"
)
task = Task(
id="analysis-task",
description="Analyze sales data trends",
expected_output="Detailed analysis report"
)
llm = OpenAIProvider(model="gpt-4")
executor = AgentExecutor(agent=agent, llm=llm)
result = executor.run(task)
print(result)
# Scaffold an agent
agx agent create researcher --role "Senior Research Analyst"
agx agent list
# Scaffold a workflow
agx workflow create research-pipeline --agents "researcher"
# Run it
agx run workflows/research-pipeline.py --verbose
from agenticx.tools import tool
@tool
def calculate_sum(x: int, y: int) -> int:
"""Calculate the sum of two numbers."""
return x + y
# Pass tools when creating agent or executor
| Command | Purpose |
|---|---|
agx | Welcome page with common commands |
agx --help | Full help |
agx project create NAME | Scaffold a project |
agx agent create NAME | Create an agent |
agx workflow create NAME | Create a workflow |
agx run FILE | Execute a workflow file |
agx serve | Start API server |
agx skills list | List installed skills |
agx hooks list | List available hooks |