Career-Ops (santifer/career-ops) is an open-source AI job search system that runs locally inside any AI coding CLI — Claude Code, Codex, OpenCode, Gemini CLI, or GitHub Copilot. It evaluates job listings against your CV using a six-dimension rubric scoring 1.0–5.0, generates ATS-optimized PDF resumes tailored per role, drafts answers to open-ended application questions on Greenhouse, Ashby, and Lever forms, scans 150+ company portals zero-token, and tracks the pipeline in a Go-based terminal dashboard. Built by Santiago Fernández de Valderrama from a real 2026 job search (740 listings, 66 applications, 12 interviews, one offer as Head of Applied AI). 50K+ stars, +477/day velocity as of June 8, 2026. Everything runs locally — no cloud, no telemetry, no account.
Career-Ops turns your AI coding agent into a job search command center. Santiago Fernández de Valderrama built it during a real 2026 job search — 740 listings evaluated, 66 applications submitted, 12 interviews, one offer (Head of Applied AI). The system survived contact with reality, and it shows: it handles the full pipeline from discovery to application to interview prep, running entirely on your machine.
The 14 skill modes cover the entire job search workflow. The listing evaluator scores jobs against your CV on six dimensions (technical fit, seniority match, domain relevance, location/remote alignment, compensation range, growth trajectory). The resume generator produces ATS-optimized PDFs tailored to each listing. The application drafter handles open-ended questions on major ATS platforms. And the pipeline dashboard gives you a terminal-based view of where everything stands.
Agentic browsing: Claude Code navigates career pages with Playwright, extracting structured job data without burning API tokens on page-scraping. Covers 150+ company portals out of the box.
CV-to-listing reasoning: Evaluation is reasoning-based, not keyword matching. The agent reads your full CV, reads the job description, and scores fit across six dimensions with explanations for each score.
Go dashboard: Pipeline state is tracked in a local Go binary — fast, terminal-native, no Electron or web app overhead. Shows listing status, scores, application dates, and interview stages.
Active job seekers who want to evaluate hundreds of listings systematically rather than manually reading each one. Career changers who need per-listing resume tailoring to highlight transferable skills. Developers who want to automate the mechanical parts of job search (portal scanning, form filling, resume formatting) while keeping strategic decisions human.
The system runs inside your coding agent’s CLI — it’s not a standalone app with a GUI. You need familiarity with Claude Code (or compatible CLI) to use it effectively. The Playwright-based portal scanning requires a local browser installation and may need updates as company career pages change their markup.
Opinionated bundle of agent personas — pre-built role templates for engineering, marketing, ops, and research teams that ship as drop-in markdown files.
OpenAI's flagship AI assistant capable of conversation, analysis, coding, writing, and multimodal reasoning across text and images.
Claude Code session memory plugin that captures context, compresses it via Agent SDK, and injects relevant memory into future sessions automatically.