aibuildai v2.5.4 — 2026-07-04

aibuildai reads a dataset and a task description and builds a model: it designs candidate models, trains them, scores them on held-out data, and writes out the best submission.

Compared to v2.5.3, this release makes aibuildai behave properly on WSL2 (Windows Subsystem for Linux) and stop more cleanly everywhere:

• Sign-in and account pages open your Windows browser on WSL2. aibuildai login and aibuildai account now launch your default Windows browser. On every machine, the page's URL is printed first — so even when no browser can open, you copy the link and continue, and a failed launch can no longer scatter error text over your terminal.
• A clear message when systemd is off. On a host without a running systemd user service — a WSL2 distro with systemd disabled, a minimal container — aibuildai run now tells you exactly what is missing and how to enable it for your environment, instead of failing with a confusing internal error.
• Ctrl-C stops cleanly. Pressing Ctrl-C while signing in or while a run is starting up now stops quietly, instead of printing an error dump.

Features

• Parallel model search. aibuildai designs several candidate models, trains and scores each on held-out data, revises the promising ones, and writes out the single best submission. Longer trainings run concurrently when your hardware has room; quick ones finish in sequence. Set the breadth in search (num_designs, parallel, num_revisions, max_nodes).
• Live terminal dashboard. Watch the search as it runs: a tree of every candidate with its status, training curves, running cost, and elapsed time. Every metric your training reports gets its own live curve tab, so you can follow each one as it moves. Arrow keys move between candidates, Tab switches panels, and you can open any candidate to read the full step-by-step trajectory of how it was built — written up as formatted text, with each step showing what was actually submitted. Ctrl+C stops the run cleanly.
• Replay a finished run. aibuildai replay <run-dir> re-opens that dashboard from the run's recorded log — no model calls, no cost. The replay faithfully reproduces the live run: the same candidate statuses, scores, and timings you saw while it ran.
• Resume a run. To pick up a prior run where it left off, set resume: <run-id> (or resume: latest) under run: in your task.yaml and run aibuildai run task.yaml again — the exit summary of an interrupted run prints the exact line to add.
• Memory across runs. aibuildai memorize task.yaml folds a task's finished runs into an editable memory file; later runs of the same task read it and build on what already worked.
• Research tools over MCP. List MCP servers under plugins.mcp_servers in your task yaml (for example a literature or dataset search) and the agents can call them while they build. Give a server a roles list to scope it to specific agents (designer, coder, reviser) instead of all of them.
• Your choice of model provider. Anthropic, DeepSeek, or any Anthropic-compatible endpoint (see Choose a model provider below).
• Time and cost caps. Bound a run by wall-clock minutes (budget.pipeline_budget_minutes) and by dollars (budget.pipeline_cost_cap_usd, budget.per_agent_cost_cap_usd); the run stops on its own when a cap is hit.
• Stays up to date. The binary updates itself to the latest release on launch, so you keep getting fixes without re-downloading by hand. Set AIBUILDAI_AUTO_UPDATE=0 to turn this off.

Upgrading from v2.0.0 (read this first)

The task is no longer described with command-line flags; it now lives in a YAML config file. The old flags are removed, and an unrecognized flag now stops the run instead of being ignored. Translate an old invocation field by field:

To upgrade an existing install, re-run the install steps below; the binary is overwritten in place and your aibuildai login session is kept.

Run a task

:::bash
aibuildai config > task.yaml      # starter config: every field with its default
# set run.task_name, run.data_root, run.instruction, run.playground_root, llm.model
aibuildai run task.yaml

Your data must already be on disk

aibuildai reads the dataset from <data_root>/<task_name>/public/. Put the files there before running — e.g. for task_name: titanic, data_root: /data: /data/titanic/public/{train.csv, test.csv, sample_submission.csv}.

• run.task_name is the dataset's directory name, not a free-text label.
• run.instruction is a plain-English description of the ML problem to solve.
• run.playground_root is where the run writes its work and the final submission, under <playground_root>/<task_name>/.

Choose a model provider

Set llm.model in task.yaml:

• Anthropic (default, claude-* ids) — set AIBUILDAI_API_KEY to your Anthropic API key (this pays for the model calls; your Max plan sign-in is a separate, also required, step — see Requirements).
• DeepSeek — a bare deepseek-* id (for example deepseek-v4-flash) routes to DeepSeek's endpoint; export your DeepSeek key as AIBUILDAI_API_KEY.
• Another Anthropic-compatible endpoint — set AIBUILDAI_BASE_URL to it and AIBUILDAI_API_KEY to its key.

Account commands

aibuildai whoami shows the signed-in account, your plan, and whether this machine can currently start a run; aibuildai logout signs out; and aibuildai account opens your plan page.

Requirements

• Linux x86_64 only (no macOS, native Windows, or ARM); on Windows, WSL2 with systemd enabled works. glibc 2.31 or newer (Ubuntu 20.04+, Debian 11+, CentOS 8+).
• 16 GB RAM; ~300 MB disk for the unpacked binary, plus room for a per-task Python environment and the run's output.
• A Max plan — sign in with aibuildai login; start a plan at https://www.aibuildai.io/#products or run aibuildai account.

Recommended (not strictly required — CPU-only training works and is fine for small tabular tasks; a GPU speeds up larger ones):

• An NVIDIA GPU with a CUDA 12.x runtime.
• conda on your PATH (install Miniconda if you do not have it).

Install

:::bash
curl -L -o aibuildai.tar.gz \
  https://github.com/aibuildai/AI-Build-AI/releases/download/v2.5.4/aibuildai-linux-x86_64-v2.5.4.tar.gz


tar -xzf aibuildai.tar.gz
cd aibuildai-linux-x86_64-v2.5.4
./install.sh                      # installs to ~/.local/bin/aibuildai

command -v aibuildai              # expect ~/.local/bin/aibuildai
# different path -> ~/.local/bin is shadowed; put it ahead on PATH
# "command not found" -> restart the shell or: source ~/.bashrc

aibuildai login    # on a server without a browser: aibuildai login --no-browser
aibuildai config > task.yaml
aibuildai run task.yaml

To uninstall: rm -rf ~/.local/bin/aibuildai ~/.local/lib/aibuildai.