AIBuildAI
  • Home
  • Products
  • Team
  • Blog
Sign In
Home Products Team Blog Sign In

Pro Guide

1. Register and subscribe

Create an account at accounts.aibuildai.io/sign-up. After signing in, go to the Billing section and switch to the Pro plan ($50 / month). Once payment is processed, your account will show an active Pro subscription.

2. Install

AIBuildAI requires a Linux x86_64 machine (Ubuntu 20.04 or newer).

curl -fsSL https://raw.githubusercontent.com/aibuildai/AI-Build-AI/main/install.sh | AIBUILDAI_LINE=v2.0 sh

3. Log in

After installation, run:

aibuildai login

This prints a link you can open in your browser to grant permission with your Pro account. To verify your login status, run aibuildai whoami — the output should show an active Pro plan.

4. Sign in to Claude Code or set your API key

If Claude Code is already signed in on this machine, no Anthropic API key is needed. AIBuildAI automatically uses the local Claude Code credentials.

If Claude Code is not signed in, run:

claude auth login

You can also use an Anthropic API key instead. This edition passes your shell environment through to the bundled Claude Code, which reads ANTHROPIC_API_KEY for itself, so that is the name to set here:

export ANTHROPIC_API_KEY=your-api-key

Add the export line to your shell profile to keep it set across sessions.

5. Run

AIBuildAI 2.0 is driven by command-line flags, not by a YAML config. There is no aibuildai config command on this edition, and --data-dir names the folder holding your data directly:

aibuildai run --task-name <name> --data-dir <path> \
  --playground-dir <path> --instruction "$(cat task.md)" --no-form

Try the worked example

The repository ships a protein EC number prediction task — predicting the enzyme class of a protein from its amino acid sequence. From a clone of the repository:

aibuildai run \
  --task-name protein-ec-prediction \
  --data-dir data/protein-ec-prediction \
  --playground-dir /path/to/playground \
  --instruction @tasks/protein-ec-prediction.md \
  --model claude-opus-5 \
  --num-candidates 3 \
  --max-agent-calls 8 \
  --run-budget-minutes 60 \
  --pipeline-budget-minutes 90 \
  --no-form

Or run aibuildai with no flags to fill in the parameters in an interactive form. For full details, see github.com/aibuildai/AI-Build-AI.

0
Skip to Content
AIBuildAI
Home
Products
Team
Blog
AIBuildAI
Home
Products
Team
Blog
Home
Products
Team
Blog

Contact

For customer support, sales inquiries, or billing questions, contact us at:

Email: support@aibuildai.io
Business: AIBuildAI
Location: San Diego, California, United States

For partnership or enterprise inquiries:

Email: contact@aibuildai.io

Hours

Monday – Friday
10am – 6pm

Follow

Facebook
Instagram
Twitter