Installation

From Source (Recommended)

git clone https://github.com/auser/agentzero
cd agentzero
cargo install --path crates/agentzero-cli

Requirements

• Rust 1.75+ (install via rustup)
• Git (for skill installation from repositories)
• Ollama or another local LLM server (for chat)

Verify Installation

az --version
# az 0.1.0

az doctor

Shell Completions

# Zsh
az completions zsh > ~/.zfunc/_az

# Bash
az completions bash > ~/.local/share/bash-completion/completions/az

# Fish
az completions fish > ~/.config/fish/completions/az.fish

LLM Provider Setup

AgentZero needs a local model server for chat. Choose one:

Ollama (Recommended)

# Install Ollama
curl -fsSL https://ollama.com/install.sh | sh

# Pull a model
ollama pull llama3.2

# Start the server
ollama serve

llama.cpp

# Start the server with your model
./llama-server -m model.gguf --host 0.0.0.0 --port 8080

vLLM

python -m vllm.entrypoints.openai.api_server --model meta-llama/Llama-3.2-3B

LM Studio

Download from lmstudio.ai, load a model, and start the local server.