Quickstart Guide¶

This guide will help you get Nevron, your autonomous AI agent, running quickly. Choose the setup path that best suits your needs:

Docker Setup (Recommended for production)
Local Setup (Recommended for development)

Prerequisites¶

Common requirements for all installation methods: - OpenAI API key (or any other API key of an LLM provider of your choice)

Additional requirements: - For Docker setup: Docker - For local setup: Python 3.13 and Poetry

Docker Setup¶

Get Nevron running with Docker in 3 steps:

1. Pull & Setup¶

# pull the latest image
docker pull axiomai/nevron:latest

# create directories for volumes
mkdir -p volumes/.chromadb

# copy example environment file
cp .env.example .env

2. Configure¶

Edit .env file with your settings:

# Required: Choose one of the LLM providers and set its API key
OPENAI_API_KEY=your_key_here    # For OpenAI
# ANTHROPIC_API_KEY=your_key_here # For Anthropic
# XAI_API_KEY=your_key_here      # For xAI
# LLAMA_API_KEY=your_key_here    # For Llama with Fireworks
# Or use local Llama with Ollama:
# LLAMA_PROVIDER=ollama
# LLAMA_OLLAMA_MODEL=llama3.1:8b

# Optional: Set the environment
ENVIRONMENT=production          # Recommended for Docker setup

# Optional: Choose memory backend
MEMORY_BACKEND_TYPE=chroma     # Default memory backend

Also, you can configure the personality, goals and rest time of your agent in .env.

AGENT_PERSONALITY="A helpful AI assistant focused on research and analysis"
AGENT_GOAL="To assist with information gathering and analysis"
AGENT_REST_TIME=300  # seconds between actions

Note: the full list of available configuration options is available in the Environment Variables documentation.

3. Run¶

docker run -d \
  --name nevron \
  -e .env \
  -v $(pwd)/volumes/.chromadb:/app/.chromadb \
  axiomai/nevron:latest

For production deployments, we recommend using Docker Compose. See our Deployment Guide for details.

Local Setup¶

Set up Nevron locally in 5 steps:

1. Clone & Install¶

# clone the repository
git clone https://github.com/axioma-ai-labs/nevron.git
cd nevron

# install Poetry if you haven't already
curl -sSL https://install.python-poetry.org | python3 -

# install dependencies
poetry install

2. Configure Environment¶

# copy example environment file
cp .env.dev .env

Required environment variables:

OPENAI_API_KEY=your_key_here    # Required for embeddings

For a complete list of available environment variables, see the Environment Variables documentation.

3. Configure Personality¶

Setup the personality, goals and rest time of your agent in .env:

AGENT_PERSONALITY="A helpful AI assistant focused on research and analysis"
AGENT_GOAL="To assist with information gathering and analysis"
AGENT_REST_TIME=300  # seconds between actions

4. Run¶

make run

Available Workflows¶

Nevron comes with two pre-configured workflows:

Analyze signal: Processes and analyzes incoming signal data
Research news: Gathers and analyzes news using Perplexity API

For more information about workflows, see the Workflows documentation.

Customization¶

You can customize Nevron by: - Adding custom workflows and tools - Adjusting planning parameters - Switching LLM providers

See the Agent Overview for more details.

Troubleshooting¶

Common issues: - Ensure all required API keys are set in .env - Check logs in the console for detailed error messages - Verify Python version: python --version (should be 3.13) - Confirm dependencies: poetry show

For more help, visit our GitHub Discussions.