Automated README summary
Automatically summarized from the README on 1 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A drop-in OpenAI API replacement that routes prompts across 540+ models for coding agents like Goose, Cursor, and VS Code Continue, with a real-time optics dashboard and token telemetry.
How it uses Jev
Jev evaluates each prompt's intent and complexity using choice, score, and noul primitives. If confidence falls below 0.60, the router refuses to downgrade and elevates to frontier safeguard models. Results drive routing decisions and cache affinity checks.
Primitives:choicescorenoul
Technique worth stealing
Break-Even Cache Affinity: computes real-time switch cost including expected cache rebuild penalty to avoid cache thrashing.
Try it
npm test to run deterministic simulation suite; runs out of the box in free local heuristic mode.
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 material0.68
- Shows a System One patternFound in material0.79
- Describes handling uncertaintynot found in the excerpt0.39
- Reports measured numbersunclear0.40
- Is a runnable toolFound in material0.90
- Top-10 learning shortlist signalnot found in the excerpt0.20
- Is a replica of the modelnot found in the excerpt0.14
- Solves a common problem (0–2)score on a 0–2 scale1.50 / 2
- About JevFound in material0.75
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 1 Oct 2026.