An early Haskell DSL that describes labeled Jev questions, renders requests and decodes matching answers.
Real data. Real impact.
Emerging
Developers
git clone https://github.com/inanna-malick/jev-dsl.gitPer week
Excellent
One command unlocks capabilities that would take hours to build.
An early Haskell DSL that describes labeled Jev questions, renders requests and decodes matching answers.
Uses inferred types and labeled handlers to connect Choice answers to predefined program branches.
Keeps questions, result types and branch handling in one inspectable definition.
The README marks it early alpha with a changing interface. Type guarantees do not establish factual correctness, and the library itself has no network transport.
Jev is TypeSafe AI's System One decision model: it returns typed scores and choices (not free text), so agents can route, filter and gate at low latency and cost.
Source: inanna-malick/jev-dsl — 7 stars, MIT. Listed by Awesome Jev.
MIT
4,600+ AI skills, agents & workflows. Install in 60 seconds. Part of the Torly.ai family.
© 2026 Torly.ai. All rights reserved.