JobQuest.AI

Your AI co-pilot for the job hunt. A desktop app that finds entry-level SDE / ML / AI jobs in India, ranks them against your resume, tracks every application, and helps with the outreach around them: cover letters, cold emails, a resume coach, and Gmail-based status updates. It runs locally, works with any of 10 LLM providers (or a local model), and ships as a single Windows .exe.

Built as a capstone project: a full-stack Python application covering data ingestion from 140+ job boards, an LLM layer with structured outputs and provider fallback, analytics, email integration, and desktop packaging.

Screenshots

Jobs, ranked against your resume	Application tracker

Dashboard + AI insights	Cold email desk

Coach (chat with files and photos)	Settings: 10 AI providers, Gmail, backups

Dark and colour themes (15 themes plus a random-palette generator)

All screenshots use the built-in demo data. Every person, company and email in them is fictional.

Features

Job search

• Pulls fresh postings from 140+ company boards: Greenhouse, Lever, Ashby, SmartRecruiters, Workday and amazon.jobs APIs, plus optional JSearch (Google for Jobs), Adzuna and Jooble keys.
• Keeps only roles in India (or remote within India) that are entry level: intern, new grad, or under 3 years. Experience requirements are parsed from the text, and "preferred" sections are ignored.
• Scores each job against your resume twice: once by skill keywords, and once by an LLM screen that returns structured output. The screen gives the real years required, a fit score, reasons, missing skills, and contacts printed in the posting.
• Filters for company tier: Big Tech (FAANG / MANGO), US unicorns with India offices, Indian startups, and mid-size companies. Also filters by role, city, posting date and internships, with one-click "Remove".
• Refreshes every 12 hours, in the app and through a Windows scheduled task.

Tracking and analytics

• A tracker with a table or board view, inline status, bulk edit and delete with undo, and Excel / CSV import and export.
• Statuses run Saved → Applied → Screening call → OA / Test → Interview → Offer, plus Rejected, Ghosted and Withdrawn.
• A dashboard of applications per day and week, a funnel, status, top companies, role families, company tiers, weekdays, sources and locations. All numbers are computed in Python. The LLM only writes the insights and advice summary, and it sees only aggregate numbers, never names.
• A daily target (default 10) with a progress ring and Windows toast reminders.

AI assistance (bring any LLM)

• 10 providers through one OpenAI-compatible layer: OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, xAI Grok, Moonshot Kimi, Mistral and OpenRouter, plus a local model through Ollama.
• Providers can be reordered, are tried in turn if one fails, and each has a test button. With none configured, every AI feature says "Please add an LLM key".
• Cover letters from the job description, your resume and any extra files, such as a LinkedIn PDF. They download as a clean PDF set in Calibri, and a local model is preferred when one is available.
• Coach, a chat that knows your profile and tracker numbers. It accepts files and photos (vision) and drafts CVs, emails and letters, which export to PDF or Word.
• Cold email desk:
  • Drop in screenshots of recruiter posts, or paste text, and it extracts each contact's name, email, title, company and the role they're hiring for.
  • It can also collect every hiring email printed in your job postings.
  • It drafts a tailored email for each contact, and a sent email counts as an application.

Email (Gmail, app password)

• Reads recent job emails without changing them. It classifies each one (rejection, OA, interview, screening, offer), matches it to tracker rows, and proposes updates for you to approve. It never moves an application backwards.
• Sends cold emails one at a time, only after you review the email and press Send.

Architecture

flowchart LR
  subgraph Desktop["JobQuestAI.exe (PyInstaller)"]
    UI["Single-page UI<br/>Bootstrap 5 + plain JS + Chart.js"] -->|REST / JSON| API["FastAPI app<br/>(local only, strict CSP)"]
    API --> DB[("SQLite<br/>jobs, tracker, settings")]
    API --> PIPE["Search pipeline<br/>sources → filters → match"]
    API --> LLM["llm.py<br/>provider table + fallback"]
    API --> STATS["stats.py<br/>pure-Python analytics"]
    API --> MAIL["mail.py<br/>IMAP read-only / SMTP send"]
    API --> LET["letters.py<br/>PDF / DOCX"]
  end
  PIPE -->|public ATS APIs| BOARDS["Greenhouse · Lever · Ashby<br/>SmartRecruiters · Workday · Amazon"]
  LLM --> PROVIDERS["OpenAI · Anthropic · Gemini · Groq · DeepSeek<br/>Grok · Kimi · Mistral · OpenRouter · Ollama"]
  MAIL --> GMAIL["Gmail"]
  SCHED["Windows Task Scheduler<br/>09:00 / 21:00"] -->|refresh + reminders| PIPE

Loading

Layer	Tech
Backend	Python 3.13, FastAPI, Uvicorn, Pydantic, SQLite (WAL)
AI	OpenAI SDK against any OpenAI-compatible endpoint, structured outputs with a JSON-mode fallback, vision input
Front end	Bootstrap 5.3, Bootstrap Icons, Chart.js 4 (vendored), plain JavaScript with no build step
Documents	pypdf, python-docx, fpdf2, openpyxl
Desktop	PyInstaller single-file exe, Edge app-mode window, WinRT toast notifications
Quality	50+ unittest tests, pyflakes, a strict Content-Security-Policy, local-only host and origin checks

Run it

Install on Windows (recommended): download JobQuestAI-Setup-1.0.0.exe from the latest release and run it.

• It installs for your user only, with no admin prompt, into %LOCALAPPDATA%\Programs\JobQuest.AI.
• It adds Start menu and optional Desktop shortcuts, and can optionally schedule a job search every 12 hours.
• Uninstall it from Settings → Apps like any other app. Your data in %USERPROFILE%\.jobhuntai is kept.

Portable: download JobQuestAI.exe from the same release and double-click it; there's nothing to install.

To build the installer yourself, run build_exe.cmd, then build_installer.cmd, which needs Inno Setup 6: winget install JRSoftware.InnoSetup.

From source:

git clone https://github.com/striderzz/JobQuest.AI.git
cd JobQuest.AI
python -m venv .venv && .venv\Scripts\activate
pip install -r requirements.txt
python -m jobhunt serve          # opens http://127.0.0.1:8000

Then:

1. Profile: upload your resume (PDF or DOCX).
2. Settings: add any AI key. Gemini, Groq and OpenRouter have free tiers, or run Ollama locally.
3. Press Find new jobs.

Try it with demo data (fictional, never touches your real data folder):

set JOBHUNT_HOME=%TEMP%\jobquest-demo
python -m jobhunt demo
python -m jobhunt serve --port 8010

Other commands: build_exe.cmd builds the exe. schedule_daily.ps1 registers the 12-hour refresh. python -m unittest discover -s tests -t . runs the tests.

How the desktop app is built

JobQuest.AI is a FastAPI web app packaged as a native-feeling Windows program.

1. One-file exe (PyInstaller). build_exe.cmd runs these steps:

• packaging/make_icon.py draws the skyscraper icon with Pillow and writes jobquestai.ico.
• python -m PyInstaller --onefile --noconsole --name JobQuestAI bundles the Python runtime, FastAPI, Uvicorn and every library into a single JobQuestAI.exe (about 34 MB).
• --add-data packs the web UI (jobhunt/static) and config.toml inside it, and --collect-submodules uvicorn keeps the server's dynamic imports.
• packaging/launcher.py is the entry point.

2. What happens on launch (jobhunt/desktop.py):

• The exe starts the FastAPI server with Uvicorn in a background thread on 127.0.0.1:8000, listening locally only.
• It opens Microsoft Edge in app mode (--app=...) with its own profile, giving a clean window with no tabs or address bar.
• It waits on that window, and closing it stops the server. If a window from an earlier run is still open, it keeps serving until that one closes too.
• A background thread runs the 12-hour job refresh, the Gmail check and the daily-target reminders (Windows toasts).
• All data stays in %USERPROFILE%\.jobhuntai, outside the exe: the SQLite database, resumes, API keys and backups. So rebuilding or reinstalling never loses anything.

3. Installer (Inno Setup). build_installer.cmd compiles packaging/installer.iss into dist\JobQuestAI-Setup-<version>.exe, which:

• installs per user with no admin prompt into %LOCALAPPDATA%\Programs\JobQuest.AI;
• adds Start menu and optional Desktop shortcuts;
• can optionally register the 09:00 / 21:00 job search as a scheduled task;
• adds a normal uninstaller (Settings → Apps) that leaves your data folder alone.

flowchart LR
  SRC["Python source<br/>jobhunt/ + static UI"] -->|PyInstaller --onefile| EXE["JobQuestAI.exe"]
  ICON["make_icon.py → .ico"] --> EXE
  EXE -->|Inno Setup| SETUP["JobQuestAI-Setup.exe"]
  EXE -->|on launch| SRV["Uvicorn + FastAPI<br/>127.0.0.1:8000"]
  EXE -->|on launch| WIN["Edge --app window"]
  SRV --> DATA[("%USERPROFILE%\.jobhuntai<br/>SQLite, resumes, keys")]

Loading

Rebuild after a code change:

build_exe.cmd
build_installer.cmd

Privacy and fair use

• Everything runs on your PC. Keys, the database, resumes and backups live in ~/.jobhuntai, outside the repo, and backups never include keys.
• Jobs come only from public job-board APIs. The app does not scrape LinkedIn, Naukri or Glassdoor, which ban it; instead it links to pre-filtered searches on those sites.
• Contact emails are only ones printed in postings or in material you provide. The app never guesses or constructs an address.
• AI calls send only what each feature needs. The dashboard insights get aggregate numbers only.
• No email is ever sent without your explicit click.

Roadmap

• Embeddings-based semantic matching alongside the keyword score
• Interview-prep packs per job (likely questions from the JD)
• macOS / Linux packaging

License

MIT. Use it, fork it, and good luck with the hunt.