Automated README summary
Automatically summarized from the README on 3 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A local service and MCP server that lets Claude Code, Claude Desktop and Codex delegate explicit decisions to JEV, TypeSafe's System One model, while logging every query on a dashboard.
How it uses Jev
The gateway builds Choice, Score or Noul questions from agent-raised options, posts them to JEV's SystemOne endpoint, and applies a risk-based confidence threshold (0.65/0.80/0.90). Above it the answer is accepted; below it the client takes its local alternative. Hooks also post spot checks directly.
Primitives:choicescorenoul
Technique worth stealing
Gate each decision by risk: accept JEV's answer only above a per-risk confidence threshold, otherwise fall back locally without repeating.
Try it
Run install.py to configure clients, then use /mcp in Claude Code; scripts/verify.sh checks setup without a paid call.
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 material0.78
- Shows a System One patternnot found in the excerpt0.11
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.97
- Top-10 learning shortlist signalnot found in the excerpt0.16
- Is a replica of the modelnot found in the excerpt0.05
- Solves a common problem (0–2)score on a 0–2 scale1.22 / 2
- About JevFound in material0.99
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 Nov 2026.