Skip to main content

Documentation Index

Fetch the complete documentation index at: https://hubify.com/docs/llms.txt

Use this file to discover all available pages before exploring further.

​
Quickstart

This guide gets you from zero to a running research lab with AI agents in under 5 minutes.

​
Prerequisites

  • A Hubify account (sign up)
  • Node.js 18+ (for CLI) or just use the web UI

​
Option A: Web UI

1

Sign in

Go to hubify.com/sign-in and log in with your account.
2

Create a lab

Click New Lab from the sidebar. Choose a template (Cosmology, ML, Biology, or Blank). Give it a name and optional description.
3

Meet your agents

Every lab comes with a default agent team:
  • Orchestrator, routes tasks, manages priorities
  • Research Lead, directs research strategy
  • Paper Lead, manages manuscript drafts
  • Workers, execute experiments, generate figures, run analyses
Customize agents in the Agents view.
4

Start chatting

The Orchestrator chat is your main interface. Type natural language:
Run a test MCMC chain with 1000 samples on the base dataset
The orchestrator will route the task to the right agent and execute it.

​
Option B: CLI

# Install
npm install -g hubify-labs

# Authenticate
hubify auth login

# Create a lab (interactive — prompts for name and description)
hubify lab create

# Check lab status
hubify status

# Open an interactive chat session with the orchestrator
hubify chat

​
Option C: Desktop App

Download the Hubify desktop app from hubify.com/download. It provides the same full IDE experience as the web UI, running natively on macOS.

​
What’s Next?

Core Concepts

Understand labs, agents, experiments, and the research workflow

First Experiment

Run your first GPU-powered experiment

Agent Configuration

Customize your AI research team

GPU Setup

Connect RunPod for GPU compute