Automated README summary
Automatically summarized from the README on 20 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
An open-source developer harness and runtime safety toolkit for AI coding agents (Antigravity, Codex, Claude Code, Cursor, VSCode, Aider). It provides context ranking, command guarding, patch review, semantic linting, Git hooks, and an MCP server.
How it uses Jev
Jev evaluates application state and natural language against typed, calibrated questions (noul, score, choice) with sub-second latency. The harness uses these judgments to rank relevant files, classify and block shell commands, audit git diffs for secrets/scope/auth/database issues, and enforce semantic lint rules in CI.
Primitives:choicescorenoul
Technique worth stealing
Use a fast, calibrated System One decision engine for high-volume filtering, safety gates, and patch triage instead of a generative LLM.
Try it
npx -y jev-dev compare
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 material0.77
- Shows a System One patternnot found in the excerpt0.25
- Describes handling uncertaintynot found in the excerpt0.07
- Reports measured numbersnot found in the excerpt0.06
- Is a runnable toolFound in material0.79
- Top-10 learning shortlist signalnot found in the excerpt0.23
- Is a replica of the modelnot found in the excerpt0.11
- Solves a common problem (0–2)score on a 0–2 scale1.94 / 2
- About JevFound in material0.94
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 20 Oct 2026.