Jev in production › SQL and data pipelines

DuckDB Dual Cognition

DuckDB extension routes SQL rows through Jev 1.13.0 for classification before caching, with a vendor-run example showing 8/8 cache hits on repeated identical queries (DuckDB Dual Cognition).

Open on GitHub ↗

8/8measured, as published by the source
Use
SQL and data pipelines
Industry
Data and analytics
Form
Open-source tool
Stage
Beta
Plugs into
DuckDB
Listed
2026-10-22
Found via
github
Repository
prasanthj/duckdb-dual-cognition
Stars
5
Forks
0
Last push
2026-10-23
Language
C++
License
Apache-2.0
DuckDB Dual Cognition screenshot
docs/images/terminal-demo.gif in the prasanthj/duckdb-dual-cognition README, Apache-2.0; shown from GitHub.

The README opens with

Compose fast, bounded System One judgments with selective System Two reasoning in one native DuckDB SQL pipeline. Classify every row cheaply, escalate only ambiguity, and keep the final value plus its decision provenance in the relation.

Semantic Resolution assigns reliable foreign keys when exact joins cannot. Give each row a bounded set of reference candidates and systemoneresolve selects the canonical key, returns ambiguous, or abstains with nomatch—with confidence and provenance attached.

Badge

For the project's own README, linking back here:

Listed in Jev in production

Also used for sql and data pipelines