Automated README summary
Automatically summarized from the README on 8 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Jevris is a local decision control plane for AI-assisted development. It sits beside coding harnesses like Claude Code, Codex, Kilo, OpenCode and Antigravity, keeping facts, arithmetic, permissions and verification in deterministic software.
How it uses Jev
Jev (TypeSafe System One) is asked only bounded questions: pick one of these, score this, or say none of the above. For example, on Claude Code one bounded Jev question, answered with confidence, can call a subagent launch low or medium risk, allowing a cheaper model for that one Agent call.
Primitives:choicescorenoul
Technique worth stealing
Keep code generation with the coding model; ask Jev only bounded, typed questions and keep verification in deterministic software.
Try it
git clone https://github.com/CryptVenture/Jevris.git && cd Jevris && npm ci --ignore-scripts && npm rebuild esbuild && npm run build && node bin/jevris.mjs install --dry-run
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 material0.80
- Shows a System One patternunclear0.46
- Describes handling uncertaintynot found in the excerpt0.06
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolFound in material0.97
- Top-10 learning shortlist signalnot found in the excerpt0.27
- Is a replica of the modelnot found in the excerpt0.15
- Solves a common problem (0–2)score on a 0–2 scale1.71 / 2
- About JevFound in material0.93
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 8 Oct 2026.