Analysis updated 2026-05-18
Research companies matching your job preferences and get a shortlist of roles automatically.
Draft tailored application answers by reusing a personal bank of your own writing.
Track every application's status by moving markdown files between folders, from a CLI or a web dashboard.
| thoughtfulllc/careerbot | alexvilelabah/bah-browser | joshuakgoldberg/eslint-plugin-erasable-syntax-only | |
|---|---|---|---|
| Stars | 51 | 51 | 51 |
| Language | TypeScript | TypeScript | TypeScript |
| Last pushed | — | — | 2026-07-01 |
| Maintenance | — | — | Active |
| Setup difficulty | easy | easy | easy |
| Complexity | 2/5 | 2/5 | 2/5 |
| Audience | general | vibe coder | developer |
Figures from each repo's GitHub metadata at analysis time.
Requires an AI agent that supports skills, such as Claude Code, to run the research and drafting commands.
Careerbot is a job-application assistant that runs as a set of AI commands inside Claude Code or any AI environment that supports skills. It researches companies that match your stated preferences, scans careers pages for open roles, and drafts application answers by pulling from a personal Answer Bank you build up over time. You own every action: the AI proposes research and drafts, but you review everything and submit each application yourself. All data lives as local markdown files organized into folders. Applications sit under one directory, company profiles under another, and reusable answers in a third. The status of an application (in-review, applied, interview, offered, rejected) is determined by which subfolder the file lives in, so moving a file between folders is the status update. Nothing is stored in a database or on a remote server. There are two ways to interact with the same files. The command-line interface uses slash commands such as /find-companies, /find-roles, and /add-application, which tell the AI to do research and write markdown. A companion web dashboard, built in Next.js, lets you browse the same files in a friendlier layout with filtering, inline editing, and click-to-change-status controls. Both stay in sync automatically because they read and write the same files on disk. Setup involves filling in a context folder with your resume, job preferences, and career background. Running /onboard walks you through that process interactively. The project is aimed at people who apply to multiple roles and want to stop rewriting the same answers every week. The source code is released under the MIT license.
An AI assistant that finds job openings matching your preferences, drafts application answers from your own material, and tracks status as markdown files.
Mainly TypeScript. The stack also includes TypeScript, Next.js, Markdown.
MIT license: free to use, copy, modify, and distribute, including commercially, as long as the copyright notice is kept.
Setup difficulty is rated easy, with roughly 30min to a first successful run.
Mainly general.
This repo across BitVibe Labs
Verify against the repo before relying on details.