Give your job search a memory.
Automate everything between your career and the Submit button. You stay in the loop. Career history, templates, tailored resumes, autofill and your own automations, in one studio.
Maestro tailors your resume from your whole career history in under a minute, and every bullet is something you actually did, so you can defend it in an interview. Then the Companion fills in the application. You press Submit.
Free and open source · No account · macOS, Linux and Windows. Watch the 37-second tour · Add the Companion to Chrome
- Same score, every time. The match score runs on fixed rules and a small model on your own computer, with no AI service involved. Same resume, same job, same number.
- It asks instead of inventing. Approved bullets go in word for word. When a job wants something your resume doesn't show, Maestro asks you about it, and every change arrives as a diff you accept or undo.
- It fills the form and stops there. The Companion fills job applications from your saved answers and attaches your resume. It never presses Submit. That click is yours.
Start here
Start with one resume. Grow into the whole studio.
1. Paste this in a terminal and press Enter.
curl -LsSf https://astral.sh/uv/install.sh | sh
export PATH="$HOME/.local/bin:$PATH"
uv tool install --python 3.12 maestro-career-studio
maestro start
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
$env:Path = "$env:USERPROFILE\.local\bin;$env:Path"
uv tool install --python 3.12 maestro-career-studio
maestro start
Maestro opens at http://localhost:3000. The first start downloads a small scoring model (about 100 MB, once), so allow a minute or two. New to the terminal? The Getting Started guide walks through every step.
2. Add your AI. Maestro needs one to read a resume or a job post. Setup opens first and suggests an OpenAI key, at about $0.01 per application. Already pay for Claude or ChatGPT? Run it from that app with no key.
3. Drop in your resumes, save a job and tailor. Here it is step by step.
Made for one person on one computer. There is no login, so anything that
can reach the app can read and change your whole career record and your saved
API keys. Out of the box it only listens on your own machine (127.0.0.1).
Never expose the app to a network (why, and the one sealed exception).
Your career record stays on your computer. When you use AI features, resume
and job information goes to the AI service you choose.
Give your AI your career
Run maestro connect. It adds Maestro to Claude Desktop, Claude Code, Codex (which the ChatGPT desktop app shares), Cursor or VS Code, and your assistant gets your career history, your resumes and your jobs. Then just ask. Without a key, this is the route: your assistant reads your resume and the job and writes the edits, and Maestro checks and saves them.
| You ask | What happens |
|---|
| Extract | "Here's a posting. Should I even apply?" | It saves the job, scores your resumes against it and flags knock-outs like visa or years of experience. |
| Maintain | "I shipped the fraud model this quarter. Add it." | A new bullet, as a draft you approve, that every resume can use. |
| Hunt | "Every morning, find new roles that fit and file the good ones." | The job-hunt skill files them to your Agent inbox. You queue or skip each one. |
| Apply | "Tailor this one, walk me through the gaps, then make the PDF." | It asks about each gap instead of inventing, keeps every change as a diff you can undo and renders the PDF. |
Ask in your own words. An apply run waits for your yes before each submit unless you turn on full automation. The MCP guide has all 94 tools and the ready-made skills for a daily hunt, an apply run and email status.
Why it works this way
If your resume folder has a v2finalcopy(3) in it, this is for you. Pasting your resume into a chat works once, then the next chat starts from scratch and rewords a little more of you out of it. Maestro keeps one record of what you have actually done, and every resume is a view of that record. Approved bullets go into a resume word for word, and rewording one is a separate step that asks you first. When a job asks for something your resume does not show, Maestro asks you about it. If it is true, it is saved for every future application. If it is not, it stays a gap.
The score is fixed rules, so the same resume and job always get the same number. It is not an employer's score or a prediction of an interview, so use it to compare your own drafts. Saving a job and tailoring for it took about 10 seconds on Gemini and about 40 on the OpenAI default in our tests, at about $0.01 (OpenAI) or under $0.03 (Gemini) per application (the numbers).
Nothing here is rented. It is free and open source (Apache 2.0), with no account, and you pay only for the AI you use. The PDFs are real LaTeX or Typst, built on your computer, and your whole history exports to one career.md file. Your career has one history. Your resume should too.
The long version, with the score, tailoring, templates and the rest of the toolkit, is in Using Maestro CS.
More, when you want it
None of this is needed to get started.
This is the beginning of the README. Read the rest at the original. Read the full README ↗
