Resume AI is a local-first resume workspace that helps you:

• track job applications in a Kanban board
• generate and edit resumes for specific roles
• save multiple resume versions to an application card
• export the latest version as PDF or DOCX

The stack runs entirely in Docker Compose and supports three AI provider modes: local Ollama, Ollama Cloud, or any OpenAI-compatible endpoint.

• Docker and Docker Compose
• An AI provider (see AI Provider Setup below)

Copy .env.example to .env and fill in your provider details:

cp .env.example .env

Choose one profile in .env:

docker compose up -d --build

Check the Kanban API health:

curl -s http://localhost:8000/health

1. Open the frontend at http://localhost:8080.
2. Create or select an application card in the Kanban board.
3. Open the Details → Resume tab.
4. Paste the job description and optional profile notes.
5. Generate a draft, edit it, save it to the card, then export it.

• Kanban board for job application tracking (CRUD, move cards, inline edit)
• AI-assisted board summaries, application tags, and next-step suggestions
• Resume generation with ATS hidden-content warnings
• Resume version history linked to application cards
• PDF and DOCX export through Pandoc

No local model download or GPU/RAM budget needed.

1. Create an API key at https://ollama.com/settings/keys.
2. In your .env:

AI_PROVIDER=ollama_cloud
OLLAMA_API_KEY=your-key-here
MODEL_NAME=gemma3:4b

Model tags are listed at https://ollama.com/library.

1. Install Ollama and start it:

ollama serve
ollama pull gemma3:1b

2. In your .env:

AI_PROVIDER=ollama
MODEL_NAME=gemma3:1b

Verify Ollama is reachable from the host:

curl -s http://localhost:11434/api/tags

AI_PROVIDER=openai
OPENAI_BASE_URL=https://api.openai.com/v1
OPENAI_API_KEY=your-key-here
MODEL_NAME=gpt-4o-mini

Basic Kanban endpoints:

curl -s http://localhost:8000/kanban/boards
curl -s http://localhost:8000/kanban/boards/1/columns
curl -s http://localhost:8000/kanban/boards/1/applications

Create a resume linked to an application card:

curl -s -X POST http://localhost:8000/resumes \
  -H 'Content-Type: application/json' \
  -d '{
        "application_id": 1,
        "job_description": "...",
        "input_profile": "...",
        "markdown": "# My Resume..."
      }'

List saved resumes for a card:

curl -s http://localhost:8000/resumes/applications/1

Export the latest saved resume:

curl -L -o resume.pdf  "http://localhost:8000/resumes/applications/1/export?format=pdf"
curl -L -o resume.docx "http://localhost:8000/resumes/applications/1/export?format=docx"

All variables are set in .env at the project root. Docker Compose reads it automatically.

AI prompts live in kanban_api/app/prompts/ as Markdown files. Edit them directly to adjust tone, format, or instructions without touching Python code.

Generated resumes and related files are saved in the local ./output directory, which is mounted into the backend container. Pandoc is installed in the kanban_api container for PDF and DOCX export.