Automated README summary
Automatically summarized from the README on 4 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
OpenJev is an opencode plugin for coding agents. It registers tools that answer bounded decisions — routing, safety checks, review verdicts, triage, scoring — with a hosted Jev decision model instead of LLM text generation, returning a choice plus a confidence score.
How it uses Jev
The agent passes a state (text) and typed questions to Jev via jev_choice, jev_noul, jev_score, or jev_ask. Jev returns probabilities and a confidence score; the plugin gates each answer as auto or escalate against default thresholds (choice/noul 0.75, score 0.65) and logs a hash of the state.
Primitives:choicescorenoul
Technique worth stealing
Ask several bounded questions in parallel on the same state, then gate answers by calibrated confidence so only confident ones auto-run.
Try it
Add "opencode-openjev" to opencode.json plugins, export TYPESAFE_API_KEY, restart opencode, run jev_doctor.
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-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
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 material0.63
- Shows a System One patternunclear0.53
- Describes handling uncertaintynot found in the excerpt0.07
- Reports measured numbersnot found in the excerpt0.03
- Is a runnable toolFound in material0.91
- Top-10 learning shortlist signalnot found in the excerpt0.20
- Is a replica of the modelnot found in the excerpt0.26
- Solves a common problem (0–2)score on a 0–2 scale1.37 / 2
- About JevFound in material0.98
no-judgment band (0.40–0.60)
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 4 Nov 2026.