> ## 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.
# Introduction
> Hubify Labs is the Scientific Discovery Platform, AI-powered research infrastructure for running experiments, writing papers, and publishing discoveries.
# Welcome to Hubify Labs
Hubify Labs is a **Scientific Discovery Platform** that gives researchers AI-powered infrastructure to run experiments, manage multi-agent teams, write papers, and publish discoveries, all from a single IDE-like interface.
## What is Hubify Labs?
Think of it as **Cursor for research**. Instead of writing code, you're running experiments, analyzing data, and publishing papers, with AI agents doing the heavy lifting.
Your research command center. See experiments, tasks, agents, and papers at a glance.
Orchestrator + lead agents + workers. Cross-model peer review. Automatic task routing.
RunPod H100/H200 integration. Auto-scaling pods. Cost optimization.
From experiment to arXiv-ready PDF. LaTeX compilation, figure generation, peer review.
## Available on Every Surface
Hubify Labs runs everywhere:
* **Web UI**, Full-featured research IDE at hubify.com
* **Desktop App**, Native macOS app (Windows coming soon)
* **CLI**, `hubify` command for terminal-first researchers
All three surfaces are equivalent, same features, same data, same agents. Pick the one that fits your workflow.
## Quick Example
```bash theme={null}
# Install the CLI
npm install -g @hubify/cli
# Login
hubify auth login
# Create a lab
hubify lab create --name "my-research" --template cosmology
# Run an experiment
hubify experiment run --name "mcmc-chain-1" --pod h100
# Check status
hubify status
```
## Key Features
| Feature | Description |
| ------------------- | ----------------------------------------------------------------------- |
| **Labs** | Isolated research environments with their own agents, data, and compute |
| **Experiments** | GPU-powered experiment execution with automatic logging and QC |
| **Agents** | Multi-agent system with orchestrator, leads, and workers |
| **Papers** | End-to-end paper pipeline from data to arXiv submission |
| **Knowledge Base** | Karpathy-style structured wiki that grows with your research |
| **Lab Sites** | Public research website at {lab}.hubify.app |
| **Novelty Scoring** | AI-powered assessment of how novel your findings are |
## Getting Started
Sign up at [hubify.com/sign-up](https://hubify.com/sign-up)
Follow the [quickstart guide](/quickstart) to set up a research lab
Set up your [agent team](/guides/agent-configuration) with the right models and roles
Launch your [first experiment](/guides/first-experiment) on GPU compute
## Architecture & Internals
For developers, contributors, and agent builders working against Hubify Labs internals, the canonical architecture references live in the [hubify repo `docs/`](https://github.com/houstongolden/hubify/tree/main/docs):
* [`architecture.md`](https://github.com/houstongolden/hubify/blob/main/docs/architecture.md), six-layer source-of-truth model: GitHub (lab filesystem), Hubify DB (structured state), Gateway (async coordination), RunPod (compute), MCP/CLI/API/SDK (agent access), Lab Sites (always-visible truth layer)
* [`github-sync.md`](https://github.com/houstongolden/hubify/blob/main/docs/github-sync.md), round-trip flow: managed repo creation, user-owned migration, webhook in, orchestrator commits out
* [`event-types.md`](https://github.com/houstongolden/hubify/blob/main/docs/event-types.md), durable `agentEvents` ledger: full type catalog, idempotency rules, mirror set, recipe for adding a new type
* [`runpod-compute.md`](https://github.com/houstongolden/hubify/blob/main/docs/runpod-compute.md), dispatch flow with budget gates, approval, recommendation, pod lifecycle, cost events
* [`lab-sites.md`](https://github.com/houstongolden/hubify/blob/main/docs/lab-sites.md), Lab Site as the always-visible truth layer; publish-mode taxonomy; subdomain + custom-domain roadmap
* [`paper-pipeline.md`](https://github.com/houstongolden/hubify/blob/main/docs/paper-pipeline.md), 14-stage paper pipeline from claim map to published
* [`adversarial-peer-review.md`](https://github.com/houstongolden/hubify/blob/main/docs/adversarial-peer-review.md), multi-role cross-model review protocol (skeptic, methods, narrative, novelty, reader)
* [`agents.md`](https://github.com/houstongolden/hubify/blob/main/docs/agents.md), orchestrator, lead, worker roles + the local-agent workflow (Claude Code, Codex, Cursor, OpenClaw)
* [`local-agent-workflow.md`](https://github.com/houstongolden/hubify/blob/main/docs/local-agent-workflow.md), how Claude Code / Codex / gh CLI consume the lab repo and round-trip back into Hubify
* [`deployment-tiers.md`](https://github.com/houstongolden/hubify/blob/main/docs/deployment-tiers.md), cloud / hybrid / sovereign deployment direction
* [`open-core-strategy.md`](https://github.com/houstongolden/hubify/blob/main/docs/open-core-strategy.md), open-core split rationale + module boundaries
* [`huggingface-roadmap.md`](https://github.com/houstongolden/hubify/blob/main/docs/huggingface-roadmap.md), HuggingFace publish integration roadmap
* [`lab-repo-manifest.md`](https://github.com/houstongolden/hubify/blob/main/docs/lab-repo-manifest.md), `hubify-lab/v1` manifest schema (`hubify.json`)
The starter lab repo template (`README.md`, `hubify.json`, `lab.md`, `agent.md`, `CLAUDE.md`, full `project-context/` set, placeholder dirs) lives in [`lab-scaffold/`](https://github.com/houstongolden/hubify/tree/main/lab-scaffold). The matching agent skill catalog is at [`skills/hubify-labs/`](https://github.com/houstongolden/hubify/tree/main/skills/hubify-labs).