agenticx-quickstartlisted
Install: claude install-skill opencue/cue
# AgenticX Quickstart
Guide for getting a user from zero to a running AgenticX agent in under 5 minutes.
## Installation
```bash
# 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]"` |
## Environment
```bash
export OPENAI_API_KEY="sk-..."
# Optional
export ANTHROPIC_API_KEY="sk-ant-..."
```
## Create a Project
```bash
agx project create my-first-agent --template basic
cd my-first-agent
agx project info
```
## Create Your First Agent (Python)
```python
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(tas