career-ops

Best for: job seekers who already use an AI coding CLI and want to run their search locally instead of pasting listings into a chat window.

Career-ops turns Claude Code, Codex, OpenCode or Antigravity into a job-search assistant. It scans job portals, scores each listing against a structured A–F rubric that resolves to a 1.0–5.0 number, tailors your CV to the roles worth applying for, and tracks applications as you go. Built by Santiago Fernandez after his own job search, and released under MIT.

What makes it useful: the inversion is the point. Companies already use AI to filter candidates; career-ops gives the candidate the same leverage to filter companies, so you spend your applications where the rubric says they are worth spending.

Where it falls short: it runs inside an agent CLI, so you need one installed and configured, plus API credits — this is not a web app you sign into. Scoring quality depends on the model you point it at, and the rubric encodes the author's judgment of what makes a good listing, which may not match yours. Expect to tune it.

Details: JavaScript, MIT licensed. Runs locally.