# Alph

> Alph is a cloud platform where Jupyter notebooks are first-class citizens. Standard .ipynb files, cloud compute via JupyterLab projects, built-in AI assistance (Claude, GPT, Gemini), GitHub sync, notebook publishing, embeddable notebooks, scheduled automations, and web app hosting — all in a multi-tenant organization workspace.

- Website: https://runalph.ai
- Documentation: https://docs.runalph.ai
- GitHub: https://github.com/alph-ai
- CLI: `pip install alphai` (PyPI: https://pypi.org/project/alphai/)
- Pricing: https://runalph.ai/pricing
- Public notebooks: https://runalph.ai/notebooks

Key facts:

- Notebooks are standard Jupyter `.ipynb` files — no proprietary format, no lock-in.
- Projects are JupyterLab servers on cloud compute (Micro 0.5 CPU/1 GB through XLarge 16 CPU/32 GB, plus GPU instances). They provide kernels, terminals, file storage, and web app hosting.
- AI is built into the editor: cell generation (`Ctrl/Cmd+K`), new cell generation (`F`/`G` for code, `S`/`D` for markdown), and a chat panel — all with notebook context. Models: Claude (Anthropic), GPT (OpenAI), Gemini (Google), selectable per conversation.
- Every project includes an AI Editor at `/{org}/{project}/ide` — an agent that can create/execute notebook cells, edit files, debug errors, install packages, and read outputs autonomously. Runs server-side; you can close your browser and check back later.
- GitHub integration via the Alph GitHub App: import notebooks from repos, bidirectional sync with cell-level diffs, pull/push/PR workflows, auto-sync.
- `gitalph.com` viewer: swap `github.com` → `gitalph.com` in any public notebook URL to get a full Alph notebook with AI and execution.
- Notebook publishing: toggle public, shareable URL at `runalph.ai/{org}/~/notebooks/{slug}`, embeddable via iframe.
- Semantic search: find notebooks and individual cells by meaning across the platform.
- Automations: schedule notebook cell ranges or AI agent prompts on a cron within a project.
- Web app hosting: start any HTTP server on port 5000 → live at `https://{org}-{project}.runalph.dev`. Custom domains with automatic SSL.
- Bring Your Own GPU: install the `alphai` CLI on any machine, run `alphai jupyter lab` to connect it to Alph via secure tunnel. No compute charges from Alph.
- Claude Code comes pre-installed in every project terminal.
- Organizations are multi-tenant workspaces with members (Owner/Admin/Member roles), shared billing, and integrations.
- Billing is credit-based (USD cents via Stripe) for compute and AI tokens.

## Docs

- [Welcome to Alph](https://docs.runalph.ai): Platform overview — what Alph is, who it's for (AI/ML engineers, data scientists, data teams), and how to get started
- [Quickstart](https://docs.runalph.ai/quickstart): Create an account, organization, notebook, and project in 5 minutes with an interactive embedded demo
- [CLI Reference](https://docs.runalph.ai/cli): Install (`pip install alphai`), authenticate (`alphai login`), start JupyterLab (`alphai jupyter lab`), and manage orgs/projects/notebooks from the terminal

## Core Concepts

- [Notebooks](https://docs.runalph.ai/concepts/notebooks): Creating, editing, and executing standard .ipynb notebooks; keyboard shortcuts; AI cell generation; publishing and sharing; semantic search; forking; export formats (ipynb, HTML, PDF, Markdown, Python)
- [Projects](https://docs.runalph.ai/concepts/projects): Cloud JupyterLab servers with configurable compute (Micro through XLarge + GPU); terminals with Claude Code; kernel management; web app hosting on port 5000 with public URLs and custom domains; local/BYO compute via CLI tunnel; automations
- [AI and Agents](https://docs.runalph.ai/concepts/ai): Built-in AI across the platform — Claude, GPT, and Gemini per-conversation; AI Editor (autonomous agent with filesystem and kernel access); cell generation shortcuts; generators for Python, terminal commands, CSV, JSON, HTML, SVG, markdown, and images
- [GitHub Sync](https://docs.runalph.ai/concepts/github-sync): Connect repos via the Alph GitHub App; import notebooks (single or bulk); bidirectional sync with cell-level diffs; pull, push, and PR workflows; auto-sync; gitalph.com viewer for any public GitHub notebook

## Guides

- [Automate Notebooks](https://docs.runalph.ai/guides/automate-notebooks): Schedule notebook cells to run on a cron — ETL pipelines, reports, model retraining, monitoring; configure cell ranges, view run history; 300s default timeout
- [Automate Agents](https://docs.runalph.ai/guides/automate-agents): Schedule AI agent prompts on a cron — the agent autonomously creates files, executes code, and iterates each run; select model and prompt per automation
- [Claude Code in Projects](https://docs.runalph.ai/guides/claude-code-remote): Use an Alph project as a remote Claude Code sandbox — pre-installed in every terminal; isolated cloud environment with persistent storage and configurable compute
- [Bring Your Own GPU](https://docs.runalph.ai/guides/bring-your-own-gpu): Connect any machine (Shadeform, Lambda, Vast.ai, RunPod, AWS EC2, local workstation) to Alph using `alphai jupyter lab`; secure outbound tunnel, no inbound ports needed
- [Deploy a Web App](https://docs.runalph.ai/guides/deploy-web-app): Go from notebook prototype to live web app — Streamlit, Gradio, FastAPI examples; public URL at `{org}-{project}.runalph.dev`; custom domains with CNAME and automatic SSL
- [Embed Notebooks](https://docs.runalph.ai/guides/embed-notebooks): Embed public notebooks via iframe; visual Embed Builder at runalph.ai/embed; URL parameters for cell selection, theme, source/output visibility; Standard (viewer connects own project) and Managed (your project powers execution) modes

## Key URLs

- [App](https://runalph.ai): Main application — sign in, create organizations, notebooks, and projects
- [Documentation](https://docs.runalph.ai): Full platform documentation (Mintlify)
- [Pricing](https://runalph.ai/pricing): Compute tiers, GPU instances, AI token rates, and self-hosted options
- [Public Notebooks](https://runalph.ai/notebooks): Browse and search all public notebooks on the platform
- [Embed Builder](https://runalph.ai/embed): Visual tool for configuring notebook embeds with live preview
- [GitHub](https://github.com/alph-ai): Open source repositories and GitHub App
- [CLI on PyPI](https://pypi.org/project/alphai/): Python CLI tool for connecting local/remote compute to Alph

## Optional

- [Anthropic Notebooks](https://docs.runalph.ai/examples/anthropic): Run Anthropic SDK examples live in Alph
- [OpenAI Notebooks](https://docs.runalph.ai/examples/openai): Run OpenAI SDK examples live in Alph
- [Qdrant Notebooks](https://docs.runalph.ai/examples/qdrant): Run Qdrant vector database examples live in Alph
- [Modal Notebooks](https://docs.runalph.ai/examples/modal): Run Modal serverless compute examples live in Alph
- [LanceDB Notebooks](https://docs.runalph.ai/examples/lancedb): Run LanceDB examples live in Alph