5-Minute Quickstart

From zero to a working AI agent in under 5 minutes. This guide walks you through installation, creating an agent, and running your first conversation.

Prerequisites

Node.js 20+ — Required for the CLI and runtime
An LLM API key — From Anthropic (Claude), OpenAI, Google (Gemini), xAI (Grok), or Mistral
Docker (optional) — For sandboxed execution

Tip: If you want to run agents without an API key, install Ollama for free local models.

Step 1: Install Nestor

Run the interactive installer. It will detect your system, prompt for API keys, and configure your environment.

# Install globally
npx nestor-sh install

# Or with pnpm
pnpm dlx nestor install

The installer will:

Create a .nestor/ configuration directory
Ask which LLM providers you want to use
Securely store your API keys
Initialize the SQLite database
Optionally pull the Docker sandbox image

Step 2: Create an Agent

Create your first agent with a name, LLM adapter, and model.

# Create a coding assistant with Claude
nestor agent create \
  --name coder \
  --adapter claude \
  --model claude-sonnet-4-6

# Or an OpenAI-based agent
nestor agent create \
  --name reviewer \
  --adapter openai \
  --model gpt-4o

# Or a local Ollama agent (free, no API key)
nestor agent create \
  --name local-helper \
  --adapter ollama \
  --model llama3.2

Tip: Run nestor agent list to see all your configured agents.

Step 3: Launch the Shell

Start an interactive conversation with your agent. The shell gives access to tools, memory, and your codebase.

# Use the default agent
nestor shell

# Or specify a specific agent
nestor shell --agent coder

# Enable dry-run mode (preview before execute)
nestor shell --dry-run

In the shell, try commands like:

Review src/auth.ts for security issues
Write unit tests for the user service
Explain the architecture of this project
Find and fix the bug in the login flow

Step 4: Launch the Studio

Start the web dashboard to monitor agents, edit workflows, and track costs visually.

# Start the Studio on port 3000
nestor start

# Custom port
nestor start --port 8080

Open http://localhost:3000 to access the Studio. From there you can:

Monitor running agents in real time
Edit DAG workflows with the visual editor
View cost analytics and token usage
Inspect trust scores and execution history

Step 5: Write and Run Tests

Nestor includes a skill testing framework. Write tests in YAML to validate agent behavior.

# Create a test file
# .nestor/tests/my-agent.test.yaml
name: My Agent Tests
agent: coder
tests:
  - name: should suggest improvements
    prompt: "Review this code: function add(a,b){return a+b}"
    expect:
      output_contains:
        - "type"
      max_iterations: 5

# Run all tests
nestor test

# Run with verbose output
nestor test --verbose

Next Steps

Learn about agent configuration — roles, tools, budgets, and more
Set up DAG workflows for multi-agent orchestration
Understand the security model including sandbox and trust scoring