Getting Started
This guide walks you through creating your first OpenVole agent in under five minutes.
Prerequisites
- Node.js 20 or later
- npm or pnpm
- An LLM provider (e.g., Ollama running locally)
Installation
Create a new directory and install OpenVole:
bash
mkdir my-agent && cd my-agent
npm init -y
npm install openvoleGlobal Install
For easier access, install globally with npm install -g openvole — then use vole directly instead of npx vole.
Initialize Your Agent
bash
npx vole initThis creates the base vole.config.json and .openvole/ directory structure.
Add Paws
A fresh OpenVole installation has zero tools, zero skills, zero opinions. Add the Paws you need:
bash
npx vole paw add @openvole/paw-brain
npx vole paw add @openvole/paw-memory
npx vole paw add @openvole/paw-dashboardConfigure
Edit vole.config.json:
json
{
"brain": "@openvole/paw-brain",
"paws": [
{
"name": "@openvole/paw-brain",
"allow": {
"network": ["*"],
"env": ["BRAIN_PROVIDER", "BRAIN_API_KEY", "BRAIN_MODEL",
"OLLAMA_HOST", "OLLAMA_MODEL", "OLLAMA_API_KEY",
"OPENAI_API_KEY", "ANTHROPIC_API_KEY", "GEMINI_API_KEY"]
}
},
{
"name": "@openvole/paw-memory",
"allow": { "env": ["VOLE_MEMORY_DIR"] }
},
{
"name": "@openvole/paw-dashboard",
"allow": { "listen": [3001], "env": ["VOLE_DASHBOARD_PORT"] }
}
],
"skills": [],
"loop": { "maxIterations": 25, "compactThreshold": 50 }
}Create a .env file with your LLM settings:
BRAIN_PROVIDER=ollama
OLLAMA_HOST=http://localhost:11434
OLLAMA_MODEL=qwen3:latestRun Your Agent
Start the interactive agent loop:
bash
npx vole startOr run a single task in headless mode (no dashboard, no channels):
bash
npx vole run "summarize my emails"Presets
Skip manual setup with a preset script:
bash
# Basic (Brain + Memory + Dashboard)
curl -fsSL https://raw.githubusercontent.com/openvole/openvole/main/presets/basic.sh | bash
# With Telegram
curl -fsSL https://raw.githubusercontent.com/openvole/openvole/main/presets/telegram.sh | bash
# Everything
curl -fsSL https://raw.githubusercontent.com/openvole/openvole/main/presets/full.sh | bashNext Steps
- Configuration — All config options explained
- Architecture — How the agent loop works
- Paws — Browse all 27 official Paws
- Skills — Add behavioral recipes from ClawHub
