Jev in production › SQL and data pipelines
signal-weave
MCP and webhook service in which Jev judges each watch item and question on an insight card against Superset BI evidence and picks the outcome, such as notify or investigate. Made 130/144 exact outcome decisions in a synthetic trial (author).
- Use
- SQL and data pipelines
- Industry
- Data and analytics
- Form
- Open-source tool
- Stage
- Beta
- Plugs into
- Apache Superset
- Listed
- 2026-09-23
- Found via
- discord
- Repository
- waddle-zoo/signal-weave
- Stars
- 4
- Forks
- 0
- Last push
- 2026-10-06
- Language
- Python
- License
- Apache-2.0
The README opens with
Typed decisions for the signals your company already has. Turn dashboards, queries, jobs, and source context into evidence-backed results.
Most companies already know what they want to watch. The hard part is not making another dashboard. It is getting an agent to understand a set of dashboards, charts, notebooks, queries, and operational signals well enough to check them, spot what matters, and run the right bounded workflow without a person opening everything every morning.
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
- jevgrep mean F1 of 0.90
- Vibefilter 1,000 rows in about a second