Teable: An AI Spreadsheet Built on Real Business Data

What Teable is

Teable is an open-source project hosted on GitHub, where it’s described simply as an AI spreadsheet for business. It’s licensed under AGPL-3.0, and the repository shows about 22,000 stars, 1,400 forks, and 2,825 commits — the profile of an actively maintained project rather than an abandoned experiment. The core idea, per the README, is a tool that stays spreadsheet-simple on the surface while running on a real PostgreSQL database underneath.

You can run it two ways. Teable operates a hosted cloud version at teable.ai, or you can self-host the whole platform on your own machines. Teable’s own site frames the goal bluntly: modern teams don’t need prettier spreadsheets, they need operational systems that can run themselves. The GitHub topic tags show where it positions itself — an Airtable alternative, a no-code and low-code tool, and an internal-tool builder.

The problem it’s built around

The README’s explanation of why Teable exists will sound familiar to anyone who has shopped for business software. You have a concrete need, you search for an app, and it covers about 70% of it. From there you either bend your process around the tool, or you file a ticket for custom development and wait quarters for it.

The project argues that the current wave of AI app generators doesn’t fix this, because each one builds in a vacuum: an empty database, no knowledge of how your team actually operates, and one more island to integrate and maintain. Teable’s answer is to put the AI where the work already happens. Your data, apps, automations, permissions, and collaborators live in one place on PostgreSQL, and the AI operates on all of it.

What the AI actually does

GitHub lists four AI features. AI Chat lets you ask questions about, analyze, and make changes to your data in natural language. The App Builder takes a description of the app you need, has an agent build it in an isolated sandbox, and deploys it to its own URL in one click. AI automations react to record changes, schedules, and webhooks, with AI steps doing the reasoning. And AI field filling generates and enriches field values in bulk.

Under the hood, a full self-hosted install bundles four platforms: an agent sandbox where every AI session runs in its own isolated container, spun up on demand and removed when the session ends; an app deployment platform where each app your team publishes runs as its own lightweight, long-lived container; the AI workflow engine; and the database collaboration platform itself — tables, views, permissions, and API.

For small businesses, the Product Hunt listing paints the clearest picture of the intent. Teams use it to build the systems they run on: gym memberships, restaurant stock, an online store’s orders. You explain your process the way you would to a new hire, and Teable builds the database and the app around it.

The spreadsheet half of the story

The AI sits on top of a full spreadsheet-style tool. GitHub lists Grid, Form, Kanban, Gallery, and Calendar views; formulas, field conversion, filtering, grouping, sorting, and aggregation; comments, record history, undo/redo, and real-time collaboration; attachments, batch editing, import/export, search, validation, charts, plugins, and SQL query. The project says it handles millions of rows without trouble.

If you’re starting from somewhere else, Teable’s 3.0 announcement says you can migrate from Airtable, spreadsheets, files, and other systems. Teable also offers an AI spreadsheet generator that turns ideas, files, and research into editable tables — a practical answer to the blank-page problem when you know you need a tracker but haven’t designed the fields yet.

Three ways to run it — and the catch

GitHub breaks deployment into three options, and the differences matter. Teable Cloud includes tables, collaboration, the API, automation, the AI features, and the App Builder. Full self-host includes all of the same, on your own machines. Standalone self-host includes tables, collaboration, the API, and automation — but not the AI features and not the App Builder.

That last point is the catch. If you self-host the lightweight version to keep costs down, you get a capable database-spreadsheet with none of the AI. The README also notes that you can hand the separate deployment repository to an AI coding agent such as Claude Code or Codex, along with a domain and access to the target machine, and it can carry the deployment end to end — though that assumes someone on your side is comfortable granting that access. A migration guide exists for standalone users who later want the full platform, and the data stays in place.

For most small businesses without technical staff, the cloud version is the realistic starting point. Self-hosting earns its keep when you already have someone managing servers and you want full control of where your data lives.

Takeaways

• Teable is open source under AGPL-3.0, with a hosted cloud option at teable.ai and a self-hosted option for teams that want full control of their data.
• The AI features — chat, automations, bulk field filling, and the app builder — operate on your live PostgreSQL data rather than on a separate, empty database.
• The standalone self-host version skips the AI features and App Builder entirely; those only come with the cloud or full self-hosted versions.