repowisemadslorentzen/ai-job-search

madslorentzen / ai-job-search

The job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.

Python★ 56,398
Use in your agentAsk this codebase

github.com/madslorentzen/ai-job-searchIndexed at 5d9e097Up to date with upstream

What is ai-job-search?

ai-job-search is an AI-powered job application framework for running a structured job search on your machine. It uses Claude Code to evaluate job postings, tailor CVs, write cover letters, and prepare for interviews. The repository primarily uses Python, with TypeScript CLI tools for job portal searches.

Written by a model from the README and the source

211 files and 1,569 symbols in 4 modules, led by TypeScript (83 files) and Python (57).

Start reading

Code health

8.1out of 10Good

This codebase scores 8.1 out of 10 for code health, which we rate good. It also scores maintainability 8.8 and static performance 9.6 out of 10. The three are scored separately and never blended into one number. Risk is concentrated, as it usually is: 34 of 211 files are git hotspots, and they average 7.0 — which is where the fixes pay off most.

Full health report

On the leaderboards:#5 of 46 Python repos

Use madslorentzen/ai-job-search in your agent

Point Claude Code, Cursor, Codex or VS Code at this repository. Your agent gets the index this page is built from: cited answers, callers, history and health for any file.

  1. 1.In Claude, open Customize → Connectors, click +, then Add custom connector. On a Team or Enterprise plan an owner adds it first under Organization settings → Connectors.
  2. 2.Paste the server URL below as the Remote MCP server URL, then click Add.
  3. 3.Click Connect. A Repowise sign-in window opens. Approve access.
  4. 4.Repowise's tools are now available in your Claude chats.

Connect with one click. Sign in with Repowise (OAuth), no API key to copy. Works in Claude on the web, desktop, and mobile.

Docs
bash
https://api.repowise.dev/mcp/madslorentzen/ai-job-search
Editors need an API key: sign in to create one.Sign in to connect

This repo is public, so anyone with a Repowise account and an API key can connect.

Try asking

  • get_overview()
  • get_answer("how is ai-job-search put together?")
  • get_why("why is ai-job-search structured this way?")

Explore ai-job-search

Key features of ai-job-search

  • ai-job-search evaluates job postings against a personal profile before drafting an application.
  • ai-job-search tailors CVs and writes cover letters in LaTeX.
  • ai-job-search uses a separate reviewer agent to research the company and critique application drafts.
  • ai-job-search compiles and visually inspects the CV and cover letter PDFs.
  • ai-job-search checks the CV PDF text layer and keyword coverage as an ATS parser would.
  • ai-job-search provides job portal search skills for Danish services such as Jobindex, Jobnet, and Akademikernes Jobbank.

How madslorentzen/ai-job-search works

The workflow starts with your profile and a job posting supplied as a URL or text. Claude Code evaluates the posting against your skills, experience, culture, location, and career alignment, then drafts a tailored CV and cover letter. The drafter-reviewer workflow uses .agents/skills/freehire-search/SKILL.md for portal skill guidance and .agents/skills/freehire-search/cli/src/cli.ts as a CLI entry point. Portal-specific commands are implemented in files such as .agents/skills/freehire-search/cli/src/commands/detail.ts. The tools/install_portal_clis.py script installs the portal CLI dependencies under .agents/skills/*/cli/. The application workflow compiles and inspects the documents, checks the CV PDF text layer, and presents the resulting files with a verification checklist.

The codebase has 211 files and 1,569 symbols in 4 modules, led by TypeScript and Python. Code health is 8.1 out of 10, rated good.

Getting started with ai-job-search

  1. Install the job search CLI tools with Python.
    python3 tools/install_portal_clis.py # Windows: python tools\install_portal_clis.py

Commands copied from the README

madslorentzen/ai-job-search FAQ

What is ai-job-search?

ai-job-search is an AI-powered framework for evaluating job postings and preparing tailored applications. It runs on your machine through Claude Code.

How does ai-job-search work?

ai-job-search compares a job posting with your profile, drafts a CV and cover letter, then uses a reviewer agent and PDF checks to refine the application.

How do I install ai-job-search?

ai-job-search installs its job search CLI tools with Python. Run python3 tools/install_portal_clis.py.

What language is ai-job-search written in?

ai-job-search is primarily written in Python. Its portal search CLI tools use TypeScript.

How is the ai-job-search code organized?

ai-job-search organizes portal skills and CLI tools under .agents, tests under tests, and installation utilities under tools. Portal CLIs include src/cli.ts entry points and command files.

Who is ai-job-search for?

ai-job-search is for people who want a structured, machine-run job application workflow. It supports profile-based evaluation, tailored documents, and interview preparation.

What license does ai-job-search use?

ai-job-search uses the MIT license.

The summary, features and answers on this page are written by a model from the README and the source, and refreshed with each index.

About this page

Get a page like this for your own codebase

Repowise built this map of madslorentzen/ai-job-search from its source and git history. It parses every symbol, draws the dependency graph, scores each file's health from complexity, duplication, coverage and churn, finds hotspots and owners in the history, and writes documentation for every module. Your coding agent reads the same index over MCP, so its answers cite real files.

Index your repo freeSee how Repowise worksFree for 2 public repos, with a page like this one.

Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed.