Automated README summary
Automatically summarized from the README on 4 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
JevGrep finds code from a description of what it does, returning verbatim source excerpts with file paths and line numbers. It runs in a terminal or as an MCP server for coding agents like Claude Code and Codex.
How it uses Jev
Jev scores eligible source fragments against a natural-language question. The provider (TypeSafe AI, Vercel AI Gateway, or OpenRouter) does the scoring; JevGrep sends fragments, the question, and repository-relative paths. Results are ranked excerpts with relevance scores, used by the CLI or the MCP tool semantic_search_code.
Primitives:score
Technique worth stealing
Score every eligible source fragment against the question and return the top verbatim excerpts with locations, within a token budget.
Try it
Run jevgrep init --global, then jevgrep init in a project, then jevgrep search --query "...".
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 projectunclear0.52
- Shows a System One patternnot found in the excerpt0.09
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersnot found in the excerpt0.11
- Is a runnable toolFound in material0.97
- Top-10 learning shortlist signalnot found in the excerpt0.18
- Is a replica of the modelnot found in the excerpt0.09
- Solves a common problem (0–2)score on a 0–2 scale1.59 / 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 4 Nov 2026.