jevbooks

← All projects

OpenJevSwift

Algorythm-Canada/OpenJevSwift · Homepage

Native Swift Jev-compatible typed-decision server for Apple silicon.

Evaluation & Benchmarking0.48Runner-up: Infra / SDKs / IntegrationsQuestionnaire
Automated README summary

Automatically summarized from the README on 11 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

OpenJevSwift is a native Swift implementation of OpenJev, the Jev-compatible "System One" decision server. It answers typed questions (noul, choice, score) about a state using model probabilities, not generated text, on Apple silicon Macs and in iPhone/Mac apps.

How it uses Jev

Jev makes decisions by reading probabilities from a model instead of generating text. For a noul question, the answer is the probability of yes; for choice or score, the probability of every option, with a confidence. The server exposes a Jev-compatible HTTP API, and the same libraries can answer requests inside an app.

Primitives:noulchoicescore

Technique worth stealing

Read answers from model probabilities rather than generating text, so answers cannot go off-schema.

Try it

swift build -c release --product openjev; .build/release/openjev serve --backend verdict

View on GitHub

Start using Jev: API key and your first request →

Model judgments from README excerpts

Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.

Models & evaluation dates

Inclusion gate
jev-1.13.0
Project signals
jev-1.13.0
Category
jev-1.13.0
Pattern tags
jev-1.13.0

Evidence

These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.

  • Jev is core to the projectFound in material0.93
  • Shows a System One patternnot found in the excerpt0.27
  • Describes handling uncertaintynot found in the excerpt0.06
  • Reports measured numbersnot found in the excerpt0.09
  • Is a runnable toolFound in material0.96
  • Top-10 learning shortlist signalunclear0.40
  • Is a replica of the modelFound in material0.82
  • Solves a common problem (0–2)score on a 0–2 scale1.08 / 2
  • About JevFound in material0.98
Signals
Jev is core to the project0.93Shows a System One pattern0.27Describes handling uncertainty0.06Reports measured numbers0.09Is a runnable tool0.96Top-10 learning shortlist signal0.40Is a replica of the model0.8200.51Solves a common problem (0–2)1.08 / 2012

no-judgment band (0.40–0.60)

Design patterns
Questionnaire0.91Check-up0.6000.51

no-judgment band (0.40–0.60)

The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 11 Oct 2026.