Quickstart¶

Go from install to a live, self-driving research project in about five minutes.

Prerequisites

A machine with git ≥ 2.38 and a working python/uv toolchain for your project. The installer bootstraps uv for you. See Install & setup for the full list.

1. Install¶

curl -fsSL https://autolab.ai/install.sh | sh

This installs the slim autolab CLI (just click, rich, httpx, pydantic). Check it:

autolab --version

autolab login

Opens a browser to sign in and stores a token for this host. On a headless box, use a token instead — see Tokens & API keys.

3. Create a project¶

Point Autolab at the code you want to optimize. From inside your repo:

cd my-research-repo
autolab init

init asks a few questions — whether to use this directory's code, the project name, the run command (how one experiment runs, e.g. python train.py), and your objective (what to optimize, e.g. minimize validation loss). It creates the project live-but-paused: it shows up on the dashboard with the agent paused.

No code yet? Start from a blank slate

autolab init --empty --objective "maximize MMLU score"

The agent writes the experiment code itself from your objective.

Scripted / non-interactive (good for agents & CI)

autolab init -y \
  --name "nanochat" \
  --objective "minimize val loss" \
  --run "python train.py" \
  --start

4. Start the agent¶

autolab start

This seeds the baseline from your code and starts the agent. Your project is now running: the agent will propose and run experiments on its own (once an execution node is attached). The first start takes the project live; afterwards, start resumes the agent after a pause.

5. Queue your own experiment¶

You don't have to wait for the agent. Make a change and submit it:

# ...edit your code...
autolab submit -m "rotary embeddings"

submit snapshots your working tree, commits it as a new experiment, and queues it. Or submit an idea and let the agent write the code:

autolab submit --nocode -m "try a cosine LR schedule"

6. Watch it run¶

autolab status      # the agent, nodes, experiment counts, and where you are
autolab log         # experiment history; → marks the experiment you're in
autolab get logs <id>   # stream an experiment's logs
autolab open        # open the project dashboard in your browser

What next?¶

Attach compute

Nothing runs without an execution node. Turn any machine into one:
```
autolab serve --project you/nanochat
```
Execution nodes
Understand the model

Why an experiment is a commit, and what "field locking" means.

Core concepts
Run experiments well

Code vs. --soft vs. --nocode, diffs, checkout, and cancel.

Run experiments
Tune the project

Objective, constraints, run command, cost caps, and collaborators.

Project settings