# AI Job Search

> An open source framework that uses Claude Code for job search and applications

- Category: Agents & dev (`agents`)
- Tags: `free`, `open-source`, `claude-code`
- Official: https://github.com/ai-job-search-dev/ai-job-search
- Wunderlust: https://wunderlust.xyz/r/ai-job-search
- Image: https://wunderlust.xyz/media/ai-job-search-poster.jpg
- Video preview: https://wunderlust.xyz/media/ai-job-search.webm
- Added: 2026-11-05

## What it is

AI Job Search is an open source framework (MIT) that turns Claude Code into an application assistant running locally: profile, job search, application, interview prep and tracking.

## What it’s for

To search and rank jobs across several boards, generate tailored CVs and cover letters, and track the pipeline.

## Benefits

- Commands to set up a profile, search jobs and rank them into a shortlist
- Generates a CV and cover letter in LaTeX compiled to PDF, with an ATS check
- Interview prep and a pipeline report in HTML or Notion

## Caveats

- Requires Claude Code (subscription or API credits), Python 3.10+, Bun and LaTeX.
- Forks of public repositories are public; the README recommends a private repository because it holds personal data.
- The example job boards are Danish; the project is not affiliated with Anthropic.

## Similar on Wunderlust

- [Agency Agents](https://wunderlust.xyz/r/agency-agents.md): Over 230 specialist agents, ready to install across many tools
- [Personal Context Portfolio](https://wunderlust.xyz/r/personal-context-portfolio.md): Ten markdown files of personal context for AI agents, with a guided interview
- [Strix](https://wunderlust.xyz/r/strix.md): Open source agent that tests app security with exploit attempts and PoCs
- [LightRAG](https://wunderlust.xyz/r/lightrag.md): A RAG framework with a knowledge graph and embeddings
- [Orca](https://wunderlust.xyz/r/orca.md): Desktop app that runs several coding agents in parallel, each in its own worktree
- [Open SEO](https://wunderlust.xyz/r/open-seo.md): An open source alternative to Semrush and Ahrefs, with MCP for agents