Browse / Job hunt / ai-job-search
ai-job-search
kevega3
Asistente de búsqueda laboral con IA que analiza vacantes, evalúa su encaje con el perfil del candidato, prioriza oportunidades, adapta CVs y filtra ofertas por salario, modalidad e idioma, además de llevar control del estado de cada postulación.
Open kevega3/ai-job-search → Matched by file structure only.
Works with any agent
ships AGENTS.md, the cross-tool instruction file.
In its own words
An AI-powered job application framework built on OpenAI Codex. Fork it, fill in your profile, and let Codex evaluate job postings, tailor your CV, write cover letters, and prepare you for interviews.
Note: This is an independent open-source project. The repository still contains historical
.claude/andCLAUDE.mdpaths for backwards compatibility, but the runtime workflow in this fork is adapted for Codex.
Current fork status
This fork is no longer just a straight Claude Code-era template. The following changes are already implemented in the repository:
- Codex migration completed via
tools/run_codex_workflow.pyandbin/*wrappers. - Candidate profile files were populated from a real CV instead of placeholders.
- Job-search evaluation now supports real-world filters such as salary growth, remote-only / hybrid-in-Bogotá preference, and excluding roles that require English.
- Blocked portals are documented in NETWORK_ACCESS.md and skipped automatically during scrape workflows.
- LinkedIn guest search is actively usable in this environment and is the main source for country-agnostic searches.
- Application tracking is persisted in
job_search_tracker.csv, and long-form review reports can be saved underreports/.
Quoting 7% of the README. Read the rest on GitHub ↗
Where it came from
What this copy built: +bin +empresas +reports — top-level directories this copy added on top of the original.
And a tool: +.hermes — configuration the original does not ship.
Read from the repository's git tree on 2026-08-17.