Top Repos· OSS alternatives· Eval· Last updated 2026-09-21

Heman10x-NGU / openJev-verdict-2.0

OSS alternative — not TypeSafe Jev. This is a public GitHub System One–class / typed-decision replica. It is not Jev and not endorsed. Closed or no-repo competitors stay on Comparisons.

“Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions (77.10% acc, 0.0636 Brier, 0.0144 ECE)”

OSS alternatives rank #10In Eval #10

• 221Stars
• —Stars Δ / 1d
• —Stars Δ / 7d
• —Stars Δ / 30d
• 33Forks
• 1Watchers

GitHub ↗Official docs ↗Back to ranking

TL;DR

Heman10x-NGU/openJev-verdict-2.0 is an independent System One–class decision engine or interface clone. Useful to study. Not TypeSafe Jev, not RLCD, not a calibration transfer.

The author describes it as: “Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions (77.10% acc, 0.0636 Brier, 0.0144 ECE)” That is their claim, not a bench this site ran.

Who it’s for

• Researchers comparing a local or open decision engine to hosted Jev — never as a silent substitute
• Agent / harness authors who need a typed gate, route, or prune step
• Quant or trading engineers who will keep ledger math in code
• Anyone who needs the unofficial line: jev.pro does not issue keys and is not TypeSafe

What’s inside

Top-level entries on GitHub at generation time: .gitattributes, .gitignore, AGENTS.md, LICENSE, README.md, RUNBOOK.md, artifacts, assets, core, data, docs, examples, export, openjev. Read those before you trust a one-line install.

How to use

1. Clone and follow the author’s Python toolchain. Do not invent a package name.

git clone https://github.com/Heman10x-NGU/openJev-verdict-2.0.git
cd openJev-verdict-2.0

2. If you compare to Jev, keep a processor label so replica rows never read as Jev scores.
3. Send a complete state and typed questions. Code owns control flow after the probabilities.

This repository is not TypeSafe Jev. Hosted Jev, for comparison only, still looks like a function call:

{
  model: "jev-1.13.0",
  state: { source: "Heman10x-NGU/openJev-verdict-2.0", brief: "..." },
  questions: {
    gate: { type: "noul", instructions: "Should we act on this state?" },
    route: { type: "choice", instructions: "Pick one next system.", criteria: ["code", "review", "human"] },
  },
}

Try this

Label a side-by-side, do not merge floors

Compare Heman10x-NGU/openJev-verdict-2.0 and hosted jev-1.13.0 on my 50 labeled tickets. Report agreement. Do not copy thresholds. Tag every row with processor=replica or processor=jev.

Schema-safe ≠ correct

On a case Heman10x-NGU/openJev-verdict-2.0 gets wrong, write down the schema-legal answer it returned and the human label. Do not “fix” it by asking Jev to generate an explanation.

FAQ

Can I treat these scores as Jev?

No. Label them as replica or local-engine results. Calibration does not transfer.

Does TypeSafe endorse it?

Their public docs index does not list it as Jev. We do not either.