Jev in production › SQL and data pipelines
jev-datafusion
Registers Jev's noul, choice, score and ask as async SQL functions on an Apache DataFusion SessionContext, so a query answers typed questions for every row through TypeSafe, OpenRouter or a compatible endpoint.
- Use
- SQL and data pipelines
- Industry
- Data and analytics
- Form
- Open-source tool
- Stage
- In production
- Plugs into
- Apache DataFusion
- Listed
- 2026-09-24
- Found via
- github
- Repository
- parable-work/jev-datafusion
- Stars
- 12
- Forks
- 1
- Last push
- 2026-09-22
- Language
- Rust
- License
- Apache-2.0
The README opens with
TypeSafe built Jev to hand software a decision instead of a paragraph: how likely something is, which option it is, or where it sits on a scale you wrote. jev-datafusion runs those decisions inside DataFusion, so you can do it at petabyte scale. That unlocks work that never fit in a single prompt. Score every open ticket. Route a year of email. Ask five questions of every meeting note and join the answers to the rest of the warehouse. A few of those queries are in Examples.
Badge
For the project's own README, linking back here:
Also used for sql and data pipelines
- JevSDSQL $0.389
- grev sub-cent cost per few thousand lines
- Jev IDS 7.7x
- jev-harness (AntonioCoppe) 1.3 seconds
- jev-ultralightspeed 41% less money
- jlink $2.95
- signal-weave 130/144 exact outcome decisions
- jevgrep mean F1 of 0.90