On-Device DuckDB Analytics
Auto-detects local files, infers schemas, and executes analytical SQL queries locally in milliseconds without database configuration.
Under Validation
Give your AI developer agents the blazing-fast DuckDB engine. Let them run on-device SQL to filter, join, and analyze local files without hitting context limits.
Concept validation only. No payment, no commitment, no recurring newsletter.
Proposed workflow
We believe that data analysis shouldn't sacrifice privacy or run up expensive cloud API token bills.
Auto-detects local files, infers schemas, and executes analytical SQL queries locally in milliseconds without database configuration.
Query, filter, and aggregate million-row logs on localhost and send only the concise, structured query result back to your agent.
Runs entirely as a local daemon. Your proprietary datasets, log files, and database dumps never touch any external network.
The honest status
The concept is being validated before development time is committed. Joining tells us the problem is relevant to you and gives you first access if the evidence supports a build.
Before you decide
The current scope, privacy model, and next step without launch-day promises.
It runs as a lightweight on-device daemon. Once installed via npm or homebrew, you add its configuration to your Claude Desktop or Cursor settings file in under a minute.
It supports CSV, Parquet, JSON-Lines (NDJSON), TSV, and Excel spreadsheets using DuckDB's fast auto-detecting file scanner.
No. The concept should state its limits clearly and preserve human review wherever judgment is required.
Your email is recorded for this experiment only. You receive one relevant update or beta invitation if the concept moves forward.
Early access
Request early beta access and lock in the €9/month special launch pricing.
Leave your email to receive the beta invitation if this concept moves forward.