Automated README summary
Automatically summarized from the README on 3 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A portable client, shared Python budget ledger, and optional harness recipes for using Jev, a System 1 model that returns typed probabilities for coding-agent decisions. For developers integrating Jev into Command Code, Claude Code, Codex, Cursor, Gemini CLI, Antigravity, OpenCode, or any MCP or shell-capable client.
How it uses Jev
Jev answers typed Noul/Choice/Score questions over a supplied state. Results are advisory only: they never grant permissions, approve commands, or certify completion. Failures return an explicit `unavailable` result, and the workflow continues as if Jev were absent. The client batches questions and uses the result in code via helpers like `guard_bash_command` or `verify_turn_completion`.
Primitives:choicescorenoul
Technique worth stealing
Batch related questions into one call; describe every option; send only relevant state; keep deterministic work in code; calibrate thresholds per question.
Try it
Install via uv tool install or pip, then run `jev setup` and `jev doctor --live`.
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 material0.94
- Shows a System One patternunclear0.49
- Describes handling uncertaintynot found in the excerpt0.06
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolFound in material0.80
- Top-10 learning shortlist signalnot found in the excerpt0.39
- Is a replica of the modelnot found in the excerpt0.06
- 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 3 Oct 2026.