aionedge.
Jev project · Community additions

jev-align (Sutro)

sutro-sh/jev-align

Dataset engineering: evaluates CSV, Parquet, and JSONL rows with Jev `Choice`, `Score`, or `Boolean` decisions, sends ambiguous and audit samples to a human, and uses accepted human labels to optimize the saved definition with GEPA.

View on GitHub ↗Project website ↗
Demo from the project README · view README ↗
GitHub stars
275 as of 2026-09-22
Forks
23
Language
Python
License
Apache-2.0
Created
2026-09-19
Last updated on GitHub
2026-09-20
Built by this organization
Sutro

What Jev does in jev-align (Sutro)

The project describes itself this way: Dataset engineering: evaluates CSV, Parquet, and JSONL rows with Jev `Choice`, `Score`, or `Boolean` decisions, sends ambiguous and audit samples to a human, and uses accepted human labels to optimize the saved definition with GEPA. In the Community additions category, Jev typically decides a single well-defined judgment, such as a label, a score or a yes/no check.

Verification

Verified. We confirmed this repository and its Jev relevance through the GitHub API and the source lists below. A specific file link has not been recorded yet.

Topics

How Community additions projects use Jev

Projects added from community lists and direct submissions. Many are small, single-purpose experiments, which makes them some of the easiest places to see how a Jev question is framed in real code.

Related Jev projects in Community additions

  1. openJev-verdict-2.0Heman10x-NGU/openJev-verdict-2.0Open decision engine: a calibrated 151M non-autoregressive model that reports beating both TypeSafe Jev and Laya on typed-decision benchmarks, shipped with its own test suite.★ 264
    Python
  2. DocJevjerryjliu/docjevDocument pipelines: LlamaIndex's open-source library that classifies a document against natural-language category rules or finds the boundaries between sub-documents, with swappable OCR backends (liteparse or LlamaParse) and a benchmark harness whose 40-document pilot classified 40/40 originals correctly at about 182 ms Jev decision p50.★ 259
    Python
  3. ai-pythonvercel-labs/ai-pythonPython ecosystem: the official Vercel AI SDK for Python carries Jev through its evaluation operation and Gateway examples.★ 185
    Python
  4. perchlakeday-org/perchSemantic linter that reads each method together with its callers and callees before asking about it. Rules are sentences in a YAML file.★ 170
    JavaScript
  5. jev-gatewayvinilana/jev-gatewayLocal gateway for Codex and Claude Code that asks Jev which tool to call next and passes everything else to your usual model.★ 170
    TypeScript
  6. Crush MonitorFerryCorleone/crush-monitorReads a WeChat conversation and labels each message with emotion and intent, rating how your own replies landed. Local, with your own key.★ 169
    TypeScript

See all 156 Community additions projects →

Where we found it