ecedalpolat/job-hunt-agent — explained in plain English
Analysis updated 2026-05-18
Search LinkedIn and Indeed postings and rank them by fit against your uploaded CV.
Generate a tailored CV and cover letter for each job you decide to apply to.
Track which jobs you have already applied to across different chat sessions.
Review and approve every application before it goes out, instead of letting the agent submit automatically.
| ecedalpolat/job-hunt-agent | 2arons/llm-cli | abe238/claude-video-plus | |
|---|---|---|---|
| Stars | 11 | 11 | 11 |
| Language | Python | Python | Python |
| Setup difficulty | moderate | easy | easy |
| Complexity | 3/5 | 2/5 | 3/5 |
| Audience | general | developer | developer |
Figures from each repo's GitHub metadata at analysis time.
Needs an API key for at least one AI provider (Anthropic, OpenRouter, or OpenAI) plus your CV file to build a profile.
Job Hunt Agent is an AI assistant built to help someone search for jobs and prepare tailored application materials for each one. It is built with a framework called LangChain deepagents, which gives it planning, memory, and the ability to hand off work to smaller specialist agents. The process starts by uploading your CV. The agent reads it and builds a master profile describing your background, which becomes the single source of truth it will always draw from when writing anything about you. It then searches job postings on sites like LinkedIn and Indeed using a free scraping tool, or an optional paid search API if the scraper gets blocked. Each posting is scored for how well it fits your profile. When you pick jobs to apply to, a separate sub agent writes a tailored CV and cover letter for each one, following a structured writing format meant to read well to both humans and automated screening systems. A key safety feature is that the agent never actually submits an application without your explicit yes or no approval first, shown either in the command line or in an included web interface built with Streamlit. The agent also remembers things across separate conversations, such as companies you are targeting or preferences you mentioned, so it will not suggest a job you already applied to even in a brand new chat session. To run it, you install it as a Python package or from source, then supply an API key for one AI provider such as Anthropic, OpenRouter, or OpenAI. Job searching itself needs no API key by default. Every step is logged, including estimated cost in dollars for each AI call, so you can track spending as you use it. This project is aimed at job seekers comfortable running a command line tool or a local web app, and it is released under the MIT license.
An AI agent that searches job postings, scores them against your CV, and writes a tailored CV and cover letter for each job you choose, with your approval before anything is submitted.
Mainly Python. The stack also includes Python, LangChain, Streamlit.
MIT license: use, copy, modify, and share freely, including commercially, as long as the copyright notice stays attached.
Setup difficulty is rated moderate, with roughly 30min to a first successful run.
Mainly general.
This repo across BitVibe Labs
double-check against the repo, no cap.