{
  "markdown": "# ![logo](https://raw.githubusercontent.com/open-and-sustainable/prismaid/main/figures/prismAId_logo.png) prismAId\n# Open Science AI Tools for Systematic, Protocol-Based Literature Reviews\n\nprismAId offers a suite of tools using generative AI models to streamline systematic reviews of scientific literature.\n\nIt provides simple-to-use, efficient, and replicable methods for screening and analyzing research papers with no coding skills required.\n\n---\n\n[![GitHub Release](https://img.shields.io/github/v/release/Open-and-Sustainable/prismAId?sort=semver&display_name=tag&style=flat)](https://github.com/Open-and-Sustainable/prismAId/releases)\n[![GitHub top language](https://img.shields.io/github/languages/top/Open-and-Sustainable/prismAId?style=flat)](https://go.dev/)\n[![Go Report Card](https://goreportcard.com/badge/github.com/open-and-sustainable/prismaid)](https://goreportcard.com/report/github.com/open-and-sustainable/prismaid)\n[![Go Reference](https://pkg.go.dev/badge/github.com/open-and-sustainable/prismaid.svg)](https://pkg.go.dev/github.com/open-and-sustainable/prismaid)\n[![PyPI - Version](https://img.shields.io/pypi/v/prismaid?logo=pypi)](https://pypi.org/project/prismaid/)\n[![R-universe status badge](https://open-and-sustainable.r-universe.dev/badges/prismaid)](https://open-and-sustainable.r-universe.dev/prismaid)\n\n[![GitHub License](https://img.shields.io/github/license/Open-and-Sustainable/prismAId?style=flat)](https://www.gnu.org/licenses/agpl-3.0.en.html#license-text)\n[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.11210796.svg)](https://doi.org/10.5281/zenodo.11210796)\n[![DOI](https://joss.theoj.org/papers/10.21105/joss.07616/status.svg)](https://doi.org/10.21105/joss.07616)\n[![DOI]( https://img.shields.io/badge/user_manual-10.5281/zenodo.15394332-blue)](https://raw.githubusercontent.com/open-and-sustainable/prismaid_manual/main/prismaid_manual.pdf)\n\n---\n\n## Toolkit Overview\nprismAId offers a comprehensive set of tools for systematic literature reviews:\n\n<div style=\"text-align: center;\">\n    <img src=\"https://raw.githubusercontent.com/open-and-sustainable/prismaid/main/figures/tools.png\" alt=\"Tools Overview\" style=\"width: 600px;\">\n</div>\n\n### Core Tools\n1. **Screening** - Filter and tag manuscripts to identify items for exclusion\n2. **Download** - Download papers from Zotero collections or from URL lists\n3. **Convert** - Convert files (PDF, DOCX, HTML) to plain text for analysis\n4. **Review** - Process systematic literature reviews based on TOML configurations\n5. **RevAIse documentation support** - Optionally document review stages as [RevAIse](https://revaise-model.readthedocs.io/stable/) review records\n\n### Workflow\nOur tools support a comprehensive systematic review workflow following the standard sequence: Search → Screen → Download → Convert → Review. RevAIse support can document Zotero download, screening, and review/extraction stages in one cumulative review record.\n\n<div style=\"text-align: center;\">\n    <img src=\"https://raw.githubusercontent.com/open-and-sustainable/prismaid/main/figures/prismAId_workflow.png\" alt=\"Workflow Diagram\" style=\"width: 600px;\">\n</div>\n\n### Access Methods\n- **AI agents via the MCP server** - A main entry point: connect an AI assistant to the [prismAId MCP server](https://prismaid.review/mcp-server.html) and drive every tool in conversation\n- **Command Line Interface** - For users who prefer terminal-based workflows\n- **Web Initializer** - A browser-based setup tool for configuring reviews\n- **Programming Libraries** - API access through multiple languages:\n  - Go (native implementation)\n  - Python package\n  - R package\n  - Julia package\n\n---\n\n## Specifications\n- **Review protocol**: Supports any literature review protocol with a preference for [PRISMA 2020](https://www.prisma-statement.org/prisma-2020), which inspired our project name.\n- **Review documentation**: Optional [RevAIse](https://revaise-model.readthedocs.io/stable/) review-record support with cumulative updates and automatic backups; see the [RevAIse integration guide](https://prismaid.review/review/revaise-integration.html).\n- **Protocol conformance**: Check RevAIse review records against reporting protocols such as PRISMA 2020, and get a protocol's full requirement checklist, using the SHACL shapes published by RevAIse; see the [conformance](https://prismaid.review/conformance.html) and [guidance](https://prismaid.review/guidance.html) docs.\n- **Distribution**: Available as:\n  - Go [package](https://pkg.go.dev/github.com/open-and-sustainable/prismaid)\n  - Python [package](https://pypi.org/project/prismaid/)\n  - R [package](https://open-and-sustainable.r-universe.dev/prismaid)\n  - Julia [package](https://github.com/JuliaRegistries/General/tree/master/P/PrismAId)\n  - 'no-coding' [binaries](https://github.com/open-and-sustainable/prismaid/releases) for Windows, MacOS, and Linux (AMD64/ARM64)\n- **Supported LLMs**:\n    1. **OpenAI**: GPT-3.5 Turbo, GPT-4 Turbo, GPT-4o, GPT-4o Mini, GPT-4.1, GPT-4.1 Mini, GPT-4.1 Nano, GPT-5, GPT-5.1, GPT-5.2, GPT-5 Mini, GPT-5 Nano, o1, o1 Mini, o3, o3 Mini, and o4 Mini\n    2. **GoogleAI**: Gemini 1.5 Pro, Gemini 1.5 Flash, Gemini 2.0 Flash, Gemini 2.0 Flash Lite, Gemini 2.5 Pro, Gemini 2.5 Flash, Gemini 2.5 Flash Lite, Gemini 3 Pro Preview, and Gemini 3 Flash Preview\n    3. **Cohere**: Command, Command Light, Command R, Command R+, Command R7B, Command R (August 2024), Command A, and Command A Reasoning\n    4. **Anthropic**: Claude 3 Sonnet, Claude 3 Opus, Claude 3 Haiku, Claude 3.5 Haiku, Claude 3.5 Sonnet, Claude 3.7 Sonnet, Claude 4.0 Sonnet, Claude 4.0 Opus, Claude 4.5 Opus, Claude 4.5 Sonnet, and Claude 4.5 Haiku\n    5. **DeepSeek**: DeepSeek Chat v3, and DeepSeek Reasoner v3\n    6. **Perplexity**: Sonar, Sonar Pro, Sonar Reasoning Pro, and Sonar Deep Research\n    7. **Cloud Providers**: AWS Bedrock, Azure AI, Vertex AI\n    8. **Self-Hosted**: OpenAI-compatible endpoints\n- **Screening capabilities**: Deduplication, language filtering, article type classification, and off-topic detection\n- **Output format**: Data in CSV or JSON formats\n- **Performance**: Efficiently processes extensive datasets with minimal setup and **no coding** required\n- **Programming Language**: Core implementation in Go with bindings for Python, R, and Julia\n\n---\n\n## Documentation\nAll information on installation, usage, and development is available at [prismaid.review](https://prismaid.review/) and in the [prismAId User Manual](https://raw.githubusercontent.com/open-and-sustainable/prismaid_manual/main/prismaid_manual.pdf).\n\n---\n\n## Credits\n### Authors\nRiccardo Boero - ribo@nilu.no\n\n### Acknowledgments\nThis project was initiated with the generous support of a SIS internal project from [NILU](https://nilu.com). Their support was crucial in starting this research and development effort. Further, acknowledgment is due for the research credits received from the [OpenAI Researcher Access Program](https://grants.openai.com/prog/openai_researcher_access_program/) and the [Cohere For AI Research Grant Program](https://share.hsforms.com/1aF5ZiZDYQqCOd8JSzhUBJQch5vw?ref=txt.cohere.com), both of which have significantly contributed to the advancement of this work.\n\n---\n\n## License\nGNU AFFERO GENERAL PUBLIC LICENSE, Version 3\n\n[![license](https://www.gnu.org/graphics/agplv3-155x51.png)](https://www.gnu.org/licenses/agpl-3.0.en.html#license-text)\n\n---\n\n## Contributing\nContributions are welcome! Please follow guidelines at [https://github.com/open-and-sustainable/prismaid?tab=contributing-ov-file](https://github.com/open-and-sustainable/prismaid?tab=contributing-ov-file).\n\n---\n\n## Citation\nBoero, R. (2024). prismAId - Open Science AI Tools for Systematic, Protocol-Based Literature Reviews. Zenodo. [DOI: 10.5281/zenodo.11210796](https://doi.org/10.5281/zenodo.11210796)\n",
  "bytes": 7818,
  "sha": "d9231e3a16c5234b0bcb5db5acf8ae4082d23e72a8f374486285e97b633add3e",
  "repo_slug": "open-and-sustainable/prismaid",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_open_and_sustainable_prismaid__022b57cb/readme"
}