Max 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 Max plan ($500 / month). Once payment is processed, your account will show an active Max 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=v2.5 sh

3. Log in

Signing in is required before running:

aibuildai login

To verify your login status, run aibuildai whoami — the output should show an active Max 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 API key instead. On this edition the key always goes in AIBUILDAI_API_KEY, whichever model provider you configure:

export AIBUILDAI_API_KEY=your-api-key

The model you select in task.yaml decides which provider's key is expected:

• Anthropic — the default. Use your Anthropic API key.
• DeepSeek — set a deepseek-* model in the config and use your DeepSeek key.

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

5. Run

AIBuildAI 2.5 is driven by a YAML config, not by command-line flags. You write a config file and pass that file to aibuildai run:

aibuildai config > task.yaml    # writes a starter config with every field
# edit task.yaml: set run.task_name, run.data_root, run.instruction, run.playground_root
aibuildai run task.yaml

Try the worked example

The repository ships tasks/protein-ec-prediction-max.yaml, a config for predicting the enzyme class (EC number) of a protein from its amino acid sequence, together with its dataset. Clone the repo, point run.data_root at the dataset folder in the clone and run.playground_root at a writable output directory, and run it:

git clone https://github.com/aibuildai/AI-Build-AI.git
cd AI-Build-AI

# Edit tasks/protein-ec-prediction-max.yaml first: set run.data_root to the
# absolute path of data/protein-ec-prediction in this clone, and
# run.playground_root to a writable output directory of your choice.
# Both ship as placeholders.
aibuildai run tasks/protein-ec-prediction-max.yaml

Other commands: aibuildai memorize to summarize past runs into memory, aibuildai replay <run-dir> to replay a finished run, and aibuildai --help for the full list. For every configuration option, see github.com/aibuildai/AI-Build-AI.