Dossier

AI Job Search is an open-source job-application framework that runs locally through Claude Code. It builds a candidate profile from documents or an interactive interview, searches supported job portals, evaluates postings against fit criteria, and uses a drafter-reviewer workflow to produce tailored CVs and cover letters in LaTeX. The workflow also supports interview preparation, application tracking, skill-gap analysis, follow-up drafts, PDF layout and ATS text-layer checks, and optional synchronization with Notion or Gmail. Its core commands include /setup, /scrape, /rank, /apply, /interview, and /outcome; the job-portal skills are extensible through generated or copied integrations. The repository is MIT-licensed and requires Claude Code plus local Python, Bun, and a LaTeX distribution for the standard workflow. It is an independent project and is not affiliated with Anthropic.

AI Job Search is an open-source, local job-application framework built around Claude Code or compatible agent tools. Users create a career profile, search and deduplicate job postings, evaluate and rank matches against structured fit criteria, and run `/apply` to produce tailored CVs and cover letters in LaTeX. The application pipeline uses a drafter–reviewer process: an agent evaluates the posting and drafts the materials, a second reviewer critiques them, and the workflow revises the output; `/interview` supports interview preparation, and optional salary benchmarking is included. The included portal-search skills target Danish services such as Jobindex, Jobnet, and Akademikernes Jobbank, while the profiling, fit-evaluation, and application workflow is described as language- and country-agnostic and adaptable to other job boards. It requires Python 3.10 or later, Bun for the job-search CLI tools, and a LaTeX distribution with `lualatex` and `xelatex`; an optional `pdftotext` installation supports the ATS parseability check for compiled CVs. The repository states that the project is independent of and unaffiliated with Anthropic or Claude Code.

Career Ops is an open-source AI job-search system that runs locally through compatible AI coding CLIs. It scans Greenhouse, Ashby, Lever, and company career pages; compares listings with a CV and evaluates them in an A–H report with a global 1–5 score. The system uses Playwright to navigate career pages, can process multiple offers with sub-agents, generates ATS-oriented CV PDFs tailored to individual job descriptions, records applications in a tracker, and researches companies and potential contacts. Its separate Block G assesses posting legitimacy, including scam or ghost-job risk, while Block H drafts additional material only for highly scored roles. It is intended to filter opportunities rather than submit applications, which users review and submit themselves.

Reactive Resume is a free, open-source resume builder for creating, updating, sharing, and exporting resumes. It provides live preview, drag-and-drop section ordering, custom sections, rich-text editing, customizable templates and styling, JSON Resume import, and PDF, JSON, and DOCX export. Resumes can be shared through unique links and the application can be self-hosted with Docker; the self-hosted stack uses PostgreSQL, with optional SeaweedFS for file uploads. The project is released under the MIT license and states that it has no tracking or analytics by default.

freehire is an open-source, self-hostable job-search platform that aggregates IT vacancies from company career pages, applicant-tracking systems, job boards, direct feeds, and Telegram channels. Its ingestion pipeline crawls sources, normalizes postings into a common schema, deduplicates them by a stable key, derives curated facets such as location, work mode, seniority, skills, and salary, and indexes them for full-text and faceted search with Meilisearch. It provides a hosted web catalogue, a keyless HTTP API, a CLI, Telegram digests, and an MCP server; the repository also includes CV creation and tailoring, deterministic CV-to-vacancy matching, application tracking, recruiter-mail linking, and an in-process assistant. The stack uses Go and Fiber, PostgreSQL with pgvector, SvelteKit, Redis, S3-compatible storage, and Docker Compose. It is MIT-licensed and can be run with the included server and standalone crawling, enrichment, embedding, indexing, and notification workers.