Organization repository on GitHub
Score how well a resume fits a job in under a second with a typed classifier (Jev), and see which requirements it covers.
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Tools & CLIs
Fast Resume Scoring
A Go CLI that scores how well a resume fits a job posting with Jev, in under a second and for about $0.0001, and shows which requirements the resume covers; the README claims roughly 18 times the speed of a frontier-model prompt.
- Stars
- 0
- Language
- Go
- License
- APACHE-2.0
- Reading time
- 2 min
- Published by
- Community
- Author
- dphbfs
- Last verified
- Oct 2026
Used inJev for HR & Recruiting
Highlights
- Scores a resume against a job posting with Jev in under a second, for about $0.0001 per score.
- Reports which job requirements the resume covers, not just a single number.
- README claims about 18x the speed of a frontier-model prompt: 20 pairs take roughly 2 s with 4 in parallel.
- Badge cites a held-out MAE of 8.6 points versus Opus 5; the full report is linked but not in the digest.
- Go and Apache-2.0 with CI and OpenSSF Scorecard badges; 0 stars, created 2026-10-12, pushed 2026-10-13.
Watch out
README and GitHub metadata reviewed 2026-10-17; the captured excerpt ends mid-bullet in the speed section, so install and usage commands, the scoring scale and the methodology behind the MAE figure are not visible here.
Questions about this entry
Short answers drawn from the linked project or page.
A Go CLI that scores how well a resume fits a job posting using Jev as a typed classifier, in under a second per score and for about $0.0001, and reports which requirements the resume covers.
The README says scoring is powered by Jev, which returns typed values the tool reads directly; the captured excerpt does not show the questions asked or the request format, so the exact decision shape is not evidenced here.
The README claims about 18 times the speed of a frontier-model prompt: under a second per score, and roughly 2 seconds for 20 pairs with 4 running in parallel. It says an Opus prompt took 76 seconds, in a sentence that is cut off.
A fit score plus which job requirements the resume covers, per the GitHub description; the digest does not show the scoring scale, the output format or example runs.
A badge cites a held-out MAE of 8.6 points versus Opus 5, and the project links a final report; the digest does not include the report's methodology, dataset or sample size, so treat the figure as the project's own.
Go, Apache-2.0 licensed, created 2026-10-12 and pushed 2026-10-13; CI and OpenSSF Scorecard badges are present, and the digest shows 0 stars.
The captured excerpt stops mid-bullet in the speed section, so install and usage commands, configuration, the comparison details and any limitations are not available here.
More Jev resources like this
A Go CLI by dorkitude that skims pages, files, and lists with Jev, keeping only the chunks that help with your stated goal. The README's example kept 4 of 40 chunks and cut 71k characters to 7.6k, an 89% saving, for whatever agent reads next.
Jev Tools & CLIs#community#github#go
Community
dorkitude/skimmerGo
dorkitude/skimmerGoGo CLI for Jev with noul, choice, score, eval, rank, and models commands: rank sends one Score question per item per weighted YAML dimension in a single request and sums weight times score in code, while threshold flags turn a failed gate into exit code 10 for scripts and CI.
Jev Tools & CLIs#community#cli#go
Community
saembit/jeff-cliGo
saembit/jeff-cliGogrep, sort, cut and uniq that match by meaning: each line whose Jev Noul clears the threshold survives grev, sibling filters route by Choice and rank by Score, and the output is always your own input, never generated text.
Jev Tools & CLIs#community#cli#coreutils
Community
aurorainfra/grevGo
aurorainfra/grevGoRead-only Go CLI that semantically checks your files against your own rules with Jev, locally or in CI, printing text or JSON and caching results between runs.
Jev Tools & CLIs#community#github#go
Community
Alurith/jeffGo
Alurith/jeffGoA single-binary gate for Impatient Programming that fails a pull request when an experienced reviewer would ask for the change to be simplified: it asks Jev about each changed file and tells the coding agent what to fix, with no LLM or parser inside.
Jev Tools & CLIs#community#github#go
Community
tools4imps/qualmGo
tools4imps/qualmGoA provider-neutral CLI, MCP server and Claude Code plugin that asks yes/no, pick-one, rate or rank questions about text and gets probabilities instead of paragraphs. Backends include Jev (TypeSafe or via OpenRouter), OpenAI's Decisions API, and Claude with an existing Claude Code login. MIT, Node 20+.
Jev Tools & CLIs#community#github#typescript
Community
adityajha2005/decisionkitTypeScript
adityajha2005/decisionkitTypeScriptFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.