A privacy-first, standalone AI-powered CV and Job Description analysis tool that runs entirely offline using LM Studio.
- Complete Privacy: All analysis happens locally - no data leaves your computer
- No API Keys Required: Uses LM Studio for local AI model inference
- Comprehensive Analysis:
- Job Description Requirements Analysis
- CV-Job Fit Assessment
- Skills Gap Identification
- CV Optimization Recommendations
- Corporate Jargon Translation
- Multiple Export Formats: TXT, DOCX, JSON
- User-Friendly Interface: Clean, modern web interface
- Standalone: Single HTML file - no installation required
- LM Studio: Download and install from lmstudio.ai
- Compatible AI Model: Any chat/completion model compatible with OpenAI API format
- Modern Web Browser: Chrome, Firefox, Safari, or Edge
- Download LM Studio from lmstudio.ai
- Install and launch the application
- Download a compatible model (recommended: Llama 2 7B or similar)
- In LM Studio, go to the "Local Server" tab
- Load your chosen model
- Start the server (default:
http://localhost:1234) - Ensure the server is running before using the tool
- Download
standalone_cv_jd_evaluator.html - Open the file in your web browser
- Click "Test Connection" to verify LM Studio connectivity
- Select your model from the dropdown
- Start analyzing!
- Configure Connection: Test and confirm LM Studio connection
- Select Model: Choose from available models in the dropdown
- Input Data:
- Job Description (required): Paste the job posting
- CV/Resume (optional): Paste your CV for matching analysis
- Additional Focus (optional): Specify particular areas of interest
- Choose Analysis Options:
- β JD Requirements Analysis
- β CV Fit Assessment (requires CV input)
- β Skills Gap Identification (requires CV input)
- β CV Optimization (requires CV input)
- β Corporate Jargon Translation
- Analyze: Click "Analyze CV-Job Match"
- Export Results: Save as TXT, DOCX, or JSON
- Technical skills breakdown
- Soft skills requirements
- Experience and qualifications
- Role responsibilities analysis
- Red flags and concerns identification
- Technical skills matching
- Experience alignment scoring
- Soft skills evidence evaluation
- Overall compatibility percentage
- Missing technical skills
- Experience shortfalls
- Recommended certifications
- Improvement suggestions
- Keyword incorporation advice
- Section reorganization tips
- Achievement highlighting
- Interview preparation questions
- Buzzword decoding
- Risk assessment (scope creep, burnout potential)
- Realistic expectation setting
- Interview clarification questions
- 100% Local Processing: All analysis happens on your computer
- No Data Transmission: Nothing is sent to external servers
- No API Keys: No cloud services or external dependencies
- Offline Capable: Works without internet connection (after initial model download)
- Operating System: Windows, macOS, or Linux
- RAM: Minimum 8GB (16GB+ recommended for larger models)
- Storage: ~4-20GB for AI models (varies by model size)
- Browser: Modern browser with JavaScript enabled
- LLaMA: All variants (7B, 13B, 70B)
- Mistral: 7B and larger
- Code Llama: For technical analysis
- Custom Models: Any model compatible with OpenAI API format
local_jd_cv_evaluator/
βββ standalone_cv_jd_evaluator.html # Main application file
βββ README.md # This documentation
βββ LICENSE # MIT license
βββ CONTRIBUTING.md # Contribution guidelines
βββ CHANGELOG.md # Version history
βββ .github/ # GitHub templates and workflows
βββ ISSUE_TEMPLATE/
βββ workflows/
"LM Studio: Not Connected" Error
- Ensure LM Studio is running
- Verify the local server is started
- Check the base URL (default:
http://localhost:1234) - Confirm a model is loaded in LM Studio
"No Models Found" Message
- Load a model in LM Studio first
- Click "Refresh Models" button
- Restart LM Studio if necessary
Analysis Takes Too Long
- Use smaller models for faster results
- Reduce input text length
- Check LM Studio performance settings
Export Features Not Working
- Ensure modern browser with JavaScript enabled
- Check popup blockers for download restrictions
- For DOCX export, verify html-docx-js library loads correctly
We welcome contributions! Please see CONTRIBUTING.md for guidelines.
- Fork this repository
- Make your changes to
standalone_cv_jd_evaluator.html - Test thoroughly with different models and inputs
- Submit a pull request with detailed description
Please use the issue templates when reporting bugs or requesting features.
This project is licensed under the MIT License - see the LICENSE file for details.
- LM Studio: For providing excellent local model inference
- OpenAI: For the standardized API format
- FontAwesome: For icons
- Google Fonts: For Inter font family
- html-docx-js: For DOCX export functionality
- Issues: GitHub Issues
- Discussions: GitHub Discussions
- Documentation: This README and inline help text
See CHANGELOG.md for detailed version history.
If you find this tool useful, please consider starring the repository!
Made with β€οΈ for privacy-conscious professionals