# LitAI
AI-powered literature review assistant that helps researchers find papers, extract key insights, and synthesize findings with proper citations.
## Overview
LitAI is a command-line tool that streamlines academic literature review by:
- Finding relevant papers through natural language search
- Extracting key claims and evidence from PDFs
- Synthesizing multiple papers to answer research questions
- Managing citations in BibTeX format
## Features
### Paper Discovery
- Search academic papers using natural language queries
- Powered by Semantic Scholar API
- View abstracts and metadata before adding to library
### Paper Management
- Build a local library of research papers
- Automatic PDF download from ArXiv
- Duplicate detection and organized storage
### AI-Powered Extraction
- Extract key claims with supporting evidence
- Automatic section references and quotes
- Cached results for instant access
### Literature Synthesis
- Generate comprehensive literature reviews
- Answer specific research questions across multiple papers
- Proper inline citations (Author et al., Year)
- Export-ready markdown format
### Natural Language Interface
- Chat-based interaction for complex queries
- Context-aware conversations about your research
- Multi-paper analysis and comparison
## Installation
### Prerequisites
- Python 3.11 or higher
- API key for OpenAI or Anthropic
### Install with pip
```bash
pip install litai
```
### Install from source
```bash
git clone https://github.com/yourusername/litai.git
cd litai
uv sync # or pip install -e .
```
## Configuration
Set your API key as an environment variable:
```bash
# For OpenAI
export OPENAI_API_KEY=sk-...
# For Anthropic
export ANTHROPIC_API_KEY=sk-ant-...
```
## Usage
Launch the interactive interface:
```bash
litai
```
### Basic Commands
```bash
# Search for papers
> /find attention mechanisms for computer vision
# Add papers to your library (by search result number)
> /add 1 3 5
# List papers in your library
> /list
# Read and extract key points from a paper
> /read 1
# Generate BibTeX citation
> /cite 1
# Synthesize multiple papers
> /synthesize Compare transformer and CNN architectures
# Natural language queries
> What are the main advantages of vision transformers over CNNs?
# Clear the screen
> /clear
# Remove papers from library
> /remove 2
```
### Advanced Usage
```bash
# Multi-paper synthesis with specific papers
> /synthesize --papers 1,3,5 How do different attention mechanisms impact performance?
# Extract key points from multiple papers at once
> /read 1 3 5
# Natural conversation mode
> Tell me about the evolution of attention mechanisms in deep learning
> Focus specifically on computer vision applications
> What papers should I read to understand this topic?
```
## Example Use Cases
### 1. Literature Review for Research Paper
*[To be added by maintainer]*
### 2. Quick Overview of a New Field
*[To be added by maintainer]*
### 3. Finding Contradictions in Literature
*[To be added by maintainer]*
### 4. Building a Reading List
*[To be added by maintainer]*
### 5. Understanding Paper Relationships
*[To be added by maintainer]*
## Data Storage
LitAI stores all data locally in `~/.litai/`:
- `litai.db` - SQLite database with paper metadata and extractions
- `pdfs/` - Downloaded PDF files
- `logs/` - Application logs for debugging
## Development
### Project Structure
```
litai/
├── src/litai/
│ ├── cli.py # Command-line interface
│ ├── database.py # Data persistence layer
│ ├── llm.py # LLM client (OpenAI/Anthropic)
│ ├── papers.py # Paper search and management
│ ├── pdf.py # PDF processing
│ ├── synthesis.py # Literature synthesis
│ └── tools.py # Extraction tools
├── tests/ # Test suite
├── docs/ # Documentation
└── pyproject.toml # Project configuration
```
### Running Tests
```bash
# Run all tests
pytest
# Run with coverage
pytest --cov=litai
# Run specific test file
pytest tests/test_papers.py
```
### Contributing
1. Fork the repository
2. Create a feature branch (`git checkout -b feature/amazing-feature`)
3. Make your changes
4. Run tests and ensure they pass
5. Update CHANGELOG.md
6. Commit your changes (`git commit -m 'Add amazing feature'`)
7. Push to the branch (`git push origin feature/amazing-feature`)
8. Open a Pull Request
## Roadmap
- TBD
## License
This project is open source and available under the [MIT License](LICENSE).
## Acknowledgments
- Built with [Semantic Scholar API](https://www.semanticscholar.org/product/api)
- Powered by OpenAI/Anthropic language models
- Beautiful CLI with Rich and Click
## Support
- Report issues: [GitHub Issues](https://github.com/harmonbhasin/litai/issues)
- Documentation: [docs/](docs/)
- Logs for debugging: `~/.litai/logs/litai.log`
---
*LitAI - Making literature review as easy as having a conversation*
Raw data
{
"_id": null,
"home_page": null,
"name": "litai-research",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.11",
"maintainer_email": null,
"keywords": "academic, papers, research, synthesis, ai, literature-review, semantic-scholar, arxiv",
"author": null,
"author_email": "Harmon Bhasin <harmonprograms@protonmail.com>",
"download_url": "https://files.pythonhosted.org/packages/12/dd/c697ce851fe781f9ee21254c1ae3adad2327534b20ac059f565670a56617/litai_research-0.1.0.tar.gz",
"platform": null,
"description": "# LitAI\n\nAI-powered literature review assistant that helps researchers find papers, extract key insights, and synthesize findings with proper citations.\n\n## Overview\n\nLitAI is a command-line tool that streamlines academic literature review by:\n- Finding relevant papers through natural language search\n- Extracting key claims and evidence from PDFs\n- Synthesizing multiple papers to answer research questions\n- Managing citations in BibTeX format\n\n## Features\n\n### Paper Discovery\n- Search academic papers using natural language queries\n- Powered by Semantic Scholar API\n- View abstracts and metadata before adding to library\n\n### Paper Management\n- Build a local library of research papers\n- Automatic PDF download from ArXiv\n- Duplicate detection and organized storage\n\n### AI-Powered Extraction\n- Extract key claims with supporting evidence\n- Automatic section references and quotes\n- Cached results for instant access\n\n### Literature Synthesis\n- Generate comprehensive literature reviews\n- Answer specific research questions across multiple papers\n- Proper inline citations (Author et al., Year)\n- Export-ready markdown format\n\n### Natural Language Interface\n- Chat-based interaction for complex queries\n- Context-aware conversations about your research\n- Multi-paper analysis and comparison\n\n## Installation\n\n### Prerequisites\n- Python 3.11 or higher\n- API key for OpenAI or Anthropic\n\n### Install with pip\n```bash\npip install litai\n```\n\n### Install from source\n```bash\ngit clone https://github.com/yourusername/litai.git\ncd litai\nuv sync # or pip install -e .\n```\n\n## Configuration\n\nSet your API key as an environment variable:\n\n```bash\n# For OpenAI\nexport OPENAI_API_KEY=sk-...\n\n# For Anthropic\nexport ANTHROPIC_API_KEY=sk-ant-...\n```\n\n## Usage\n\nLaunch the interactive interface:\n```bash\nlitai\n```\n\n### Basic Commands\n\n```bash\n# Search for papers\n> /find attention mechanisms for computer vision\n\n# Add papers to your library (by search result number)\n> /add 1 3 5\n\n# List papers in your library\n> /list\n\n# Read and extract key points from a paper\n> /read 1\n\n# Generate BibTeX citation\n> /cite 1\n\n# Synthesize multiple papers\n> /synthesize Compare transformer and CNN architectures\n\n# Natural language queries\n> What are the main advantages of vision transformers over CNNs?\n\n# Clear the screen\n> /clear\n\n# Remove papers from library\n> /remove 2\n```\n\n### Advanced Usage\n\n```bash\n# Multi-paper synthesis with specific papers\n> /synthesize --papers 1,3,5 How do different attention mechanisms impact performance?\n\n# Extract key points from multiple papers at once\n> /read 1 3 5\n\n# Natural conversation mode\n> Tell me about the evolution of attention mechanisms in deep learning\n> Focus specifically on computer vision applications\n> What papers should I read to understand this topic?\n```\n\n## Example Use Cases\n\n### 1. Literature Review for Research Paper\n*[To be added by maintainer]*\n\n### 2. Quick Overview of a New Field\n*[To be added by maintainer]*\n\n### 3. Finding Contradictions in Literature\n*[To be added by maintainer]*\n\n### 4. Building a Reading List\n*[To be added by maintainer]*\n\n### 5. Understanding Paper Relationships\n*[To be added by maintainer]*\n\n## Data Storage\n\nLitAI stores all data locally in `~/.litai/`:\n- `litai.db` - SQLite database with paper metadata and extractions\n- `pdfs/` - Downloaded PDF files\n- `logs/` - Application logs for debugging\n\n## Development\n\n### Project Structure\n```\nlitai/\n\u251c\u2500\u2500 src/litai/\n\u2502 \u251c\u2500\u2500 cli.py # Command-line interface\n\u2502 \u251c\u2500\u2500 database.py # Data persistence layer\n\u2502 \u251c\u2500\u2500 llm.py # LLM client (OpenAI/Anthropic)\n\u2502 \u251c\u2500\u2500 papers.py # Paper search and management\n\u2502 \u251c\u2500\u2500 pdf.py # PDF processing\n\u2502 \u251c\u2500\u2500 synthesis.py # Literature synthesis\n\u2502 \u2514\u2500\u2500 tools.py # Extraction tools\n\u251c\u2500\u2500 tests/ # Test suite\n\u251c\u2500\u2500 docs/ # Documentation\n\u2514\u2500\u2500 pyproject.toml # Project configuration\n```\n\n### Running Tests\n```bash\n# Run all tests\npytest\n\n# Run with coverage\npytest --cov=litai\n\n# Run specific test file\npytest tests/test_papers.py\n```\n\n### Contributing\n1. Fork the repository\n2. Create a feature branch (`git checkout -b feature/amazing-feature`)\n3. Make your changes\n4. Run tests and ensure they pass\n5. Update CHANGELOG.md\n6. Commit your changes (`git commit -m 'Add amazing feature'`)\n7. Push to the branch (`git push origin feature/amazing-feature`)\n8. Open a Pull Request\n\n## Roadmap\n\n- TBD\n\n## License\n\nThis project is open source and available under the [MIT License](LICENSE).\n\n## Acknowledgments\n\n- Built with [Semantic Scholar API](https://www.semanticscholar.org/product/api)\n- Powered by OpenAI/Anthropic language models\n- Beautiful CLI with Rich and Click\n\n## Support\n\n- Report issues: [GitHub Issues](https://github.com/harmonbhasin/litai/issues)\n- Documentation: [docs/](docs/)\n- Logs for debugging: `~/.litai/logs/litai.log`\n\n---\n\n*LitAI - Making literature review as easy as having a conversation*\n",
"bugtrack_url": null,
"license": null,
"summary": "AI-powered academic paper synthesis tool",
"version": "0.1.0",
"project_urls": {
"Documentation": "https://github.com/harmonbhasin/litai/blob/main/README.md",
"Homepage": "https://github.com/harmonbhasin/litai",
"Issues": "https://github.com/harmonbhasin/litai/issues",
"Repository": "https://github.com/harmonbhasin/litai"
},
"split_keywords": [
"academic",
" papers",
" research",
" synthesis",
" ai",
" literature-review",
" semantic-scholar",
" arxiv"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "84ea9087664cb0c7ddb372e1ae1d62fbc7de6ae082eb52ca4a114cd0234da79e",
"md5": "1f563413f08de49fe96ebb373ed19511",
"sha256": "6e6def5657e75c5d37579c7a6f63c51421c0f8ab668a4cf82b59abef45dbf474"
},
"downloads": -1,
"filename": "litai_research-0.1.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "1f563413f08de49fe96ebb373ed19511",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.11",
"size": 37172,
"upload_time": "2025-08-01T20:27:41",
"upload_time_iso_8601": "2025-08-01T20:27:41.438246Z",
"url": "https://files.pythonhosted.org/packages/84/ea/9087664cb0c7ddb372e1ae1d62fbc7de6ae082eb52ca4a114cd0234da79e/litai_research-0.1.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "12ddc697ce851fe781f9ee21254c1ae3adad2327534b20ac059f565670a56617",
"md5": "bfe55837893ca08cd2cc8e91f6ee1e8b",
"sha256": "a5321e1591ed663478746f5d0f743c1474f78c484896db7b109080d557f1fd53"
},
"downloads": -1,
"filename": "litai_research-0.1.0.tar.gz",
"has_sig": false,
"md5_digest": "bfe55837893ca08cd2cc8e91f6ee1e8b",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.11",
"size": 43274,
"upload_time": "2025-08-01T20:27:42",
"upload_time_iso_8601": "2025-08-01T20:27:42.799935Z",
"url": "https://files.pythonhosted.org/packages/12/dd/c697ce851fe781f9ee21254c1ae3adad2327534b20ac059f565670a56617/litai_research-0.1.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-01 20:27:42",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "harmonbhasin",
"github_project": "litai",
"github_not_found": true,
"lcname": "litai-research"
}
JSON
