career-ops — What is it?

Career-Ops is an AI-powered job search system that evaluates job offers, generates tailored CVs, and manages job applications efficiently.

⭐ 44,350 Stars 🍴 9,316 Forks JavaScript MIT Author: santifer
Source: README View on GitHub →

Why it matters

Career-Ops is gaining attention due to its innovative use of AI to streamline the job search process, addressing the pain points of manual application tracking and the need for personalized CVs. Its unique technical choice of integrating Claude Code and Playwright for automated job portal scanning and CV generation stands out.

Source: Synthesis of README and project traits

Core Features

AI-powered Evaluation

Career-Ops uses Claude Code to evaluate job offers with a structured A-F scoring system, considering 10 weighted dimensions, and provides a recommendation based on the score.

Source: README
PDF Generation

The system generates ATS-optimized CVs with keyword-injected content and a specific design to ensure they pass through Applicant Tracking Systems (ATS).

Source: README
Portal Scanner

Career-Ops can scan job portals like Greenhouse, Ashby, Lever, and Wellfound, as well as custom company pages, to find new job offers.

Source: README
Batch Processing

The system supports batch processing of multiple job offers in parallel, using sub-agents to evaluate them simultaneously.

Source: README
Dashboard TUI

A terminal UI allows users to browse, filter, and sort their job application pipeline, providing a comprehensive overview of their job search progress.

Source: README

Architecture

The architecture of Career-Ops suggests a modular design with Claude Code as the central AI component, integrated with Playwright for web automation. The system uses a combination of command-line interfaces and a terminal UI for user interaction. Data flow is managed through a structured pipeline that includes CV parsing, offer evaluation, and PDF generation.

Source: Code tree + dependency files

Tech Stack

infra: Not enough information.  |  key_deps: @google/generative-ai, dotenv, js-yaml, playwright  |  language: JavaScript  |  framework: Claude Code, Playwright

Source: Dependency files + code tree

Quick Start

git clone https://github.com/santifer/career-ops.git cd career-ops && npm install npx playwright install chromium npm run doctor cp config/profile.example.yml config/profile.yml cp templates/portals.example.yml portals.yml Create cv.md in the project root with your CV in markdown claude /career-ops /career-ops {paste a JD} /career-ops scan /career-ops pdf /career-ops batch /career-ops tracker /career-ops apply /career-ops pipeline /career-ops contacto /career-ops deep /career-ops training /career-ops project
Source: README Installation/Quick Start

Use Cases

Career-Ops is suitable for job seekers looking to automate and streamline their job search process. It is useful for those who want personalized CVs and efficient evaluation of job offers. The system can be particularly beneficial for professionals in tech and AI-related fields.

Source: README

Strengths & Limitations

Strengths

  • Strength 1: Automates and streamlines the job search process
  • Strength 2: Provides personalized CVs optimized for ATS
  • Strength 3: Integrates AI for efficient job offer evaluation

Limitations

  • Limitation 1: Requires initial setup and configuration
  • Limitation 2: May not cover all job portals
  • Limitation 3: Relies on the accuracy of the AI model for evaluations
Source: Synthesis of README, code structure and dependencies

Latest Release

v1.6.0 (2026-04-26): Added Gemini CLI native integration and evaluation features.

Source: GitHub Releases

Verdict

Career-Ops is a promising project for job seekers aiming to leverage AI to enhance their job search efficiency. Its integration of Claude Code and Playwright showcases innovative use of AI in the job search domain. It is particularly suitable for tech professionals who value automation and personalization in their job search process.

Transparency Notice
This page is auto-generated by AI (a large language model) from the following public materials: GitHub README, code tree, dependency files and release notes. Analyzed at: 2026-04-28 12:33. Quality score: 85/100.

Data sources: README, GitHub API, dependency files