SQLite Editor · for VS Code, Cursor, VSCodium and Windsurf

Ask your SQLite database in plain English. Get SQL you can run.

Open any .db file inside your editor, read what it holds, edit it like a spreadsheet, and ask "which accounts owe us money?" instead of writing four joins by hand. When a query fails, it tells you why and hands you the fix.

The AI chat: the question "Which accounts owe us money right now?" turned into a SQL query joining accounts, subscriptions, plans and invoices, already run, with the result grid on the left

Why I built it

Every other SQLite editor still makes you write SQL by hand

I work with SQLite databases every day. Every time I wanted to ask a simple question of my own data, I bounced between a read-only browser and a SQL prompt. The viewers had no idea what the data meant. The query consoles had no idea what schema was in front of them.

So I built the database editor I wanted to use. It opens the file inside VS Code as a grid you can edit, and on top of that it reads the schema and a few sample rows, so the model talks about your tables, not tables in general.

Ciro Cesar Maciel, who builds and maintains it

How it works

From a .db file to the answer, without leaving the editor

1

Open

Click a .db, .sqlite or .sqlite3 file in the Explorer. It opens as a grid. No import, no separate app.

2

Read the briefing

One click and it tells you what the database is for, which tables matter and what looks odd in the samples.

3

Ask

Press Cmd+K (Ctrl+K) and type the question the way you would ask a colleague.

4

Review and run

The SQL comes back explained in one sentence. Nothing runs until you press Run.

See it in action

A question in plain English becomes SQL, and one click runs it

It knew the amount lives in amount_cents, that you need two joins to get from an invoice to an account, and that dollars means dividing by 100. A real run:

What went in

Which accounts owe us money right now? Show the account, plan, how many invoices are open and the total in dollars, biggest first.

What came out

SELECT a.name AS account_name, p.name AS plan_name,
  COUNT(i.id) AS open_invoices_count,
  ROUND(SUM(i.amount_cents) / 100.0, 2) AS total_owed_dollars
FROM accounts a
JOIN subscriptions s ON a.id = s.account_id
JOIN plans p ON s.plan_id = p.id
JOIN invoices i ON s.id = i.subscription_id
WHERE i.status != 'paid' AND i.paid_at IS NULL
GROUP BY a.id, p.id
ORDER BY total_owed_dollars DESC
A plain-English question answered with SQL and its result grid

And then

A failed query, the reason in one sentence, the fix ready to run

When SQLite says "no such column", it reads your schema and tells you which column you meant. Apply fix & run does the rest.

What went in

no such column: i.amount

What came out

The column `amount` does not exist; the correct column name is `amount_cents`.
SELECT a.name, SUM(i.amount_cents) / 100.0 AS owed FROM invoices i ...
The Fix this error dialog: the SQLite error, the explanation that the column is amount_cents, and the corrected SQL with Apply fix and run

And then

Open a database you have never seen and understand it in a minute

The Data Briefing reads the schema and samples and says, in plain English, what the database is for, which tables matter and why, and which questions you might want to ask. Click a question and it goes straight to the chat.

The Data Briefing panel over a billing database: what it is, a summary in plain English and the main tables

Everything in it

A full SQLite client, with the AI one click away

Edit like a spreadsheet

Browse tables, edit cells, insert and delete rows, alter tables, create indexes and run custom queries. Changes are written to the file.

Ask in plain English

The chat writes SQL against your real schema, explains it in one sentence and keeps the thread, so you can refine with follow-ups. Run, Explain, Copy SQL.

Errors explained and fixed

When a query fails, Ask AI to fix names the problem and proposes corrected SQL. Apply fix & run runs it.

Data Briefing

What the database is for, which tables matter, what looks odd, which questions to ask. One click.

Insights on every table

When you open a table, one scan flags anomalies, data-quality issues and patterns above the grid. You can turn it off.

Filter and edit by intent

AI Filter filters a table with a plain-English predicate. AI Edit transforms a column with an instruction like "trim whitespace", and you can undo it.

Schema Insights

Finds missing indexes on foreign-key columns, CHECK candidates and other structure smells, with the DDL to Apply or Copy.

Your model, or ours

Free: any model on OpenRouter with your own key, pay per token. Pro: the AI included, no account, no key.

Before you choose

How it compares

SQLite Editor

DB Browser for SQLite

DBeaver

SQLTools

Open a .db inside VS CodeYesNo: separate appNo: separate appPartial: via driver
Inline row editingYesYesYesNo
Schema and structure managementYesYesYesPartial
Plain English to SQLYesNoNoPartial: paid add-on
Schema-aware AI briefingYesNoNoNo
AI explanation of SQL errorsYesNoNoNo

From each tool’s public listing. Something changed? Tell me at ciromaciel.click/contact.

Free and Pro

Free does everything. Pro skips the AI account.

The free version keeps every feature, with your own OpenRouter key. Pro is for when you would rather not create one more account and paste one more key: the AI comes included.

Free

$0

  • The whole editor: grid, edits, alter, indexes, queries
  • Every AI feature with your own OpenRouter key, any model, pay per token
  • The grid, the edits and the queries run on your machine
Install free

Pro

  • Every AI feature with no OpenRouter account and no key

  • One license key, any editor; it also unlocks Stack Trace Triage Pro if you subscribe to both

  • Claude Haiku 5.5, up to 50 AI requests a day

Loading the price…

Questions

Before you install

Try it on the next .db file you open.

All 11 extensions