Open-source AI research assistant for VS Code + GitHub Copilot. Connects to PubMed, OpenAlex, Semantic Scholar, Europe PMC, CrossRef, and Zotero via MCP servers. Custom agents guide systematic reviews, academic writing, data analysis, and project management — all ICMJE-compliant with full audit trails.
Assists with academic manuscript preparation while maintaining strict ICMJE compliance. Scaffolds Quarto documents, manages citations via Zotero, helps draft sections, generates AI disclosure statements, and tracks AI contributions for authorship accountability.
Guides researchers through structured critical appraisal of individual studies using validated checklists (CASP, JBI, STROBE, CONSORT, etc.). Extracts evidence from PDF annotations, generates appraisal reports, and supports cross-study synthesis.
Supports statistical analysis and data engineering for research projects. Generates reproducible R or Python analysis scripts in Quarto documents. Covers descriptive statistics, regression, survival analysis, meta-analysis, and visualization.
Helps resolve bugs, implement new features, and improve the RWA codebase. Gathers requirements first, then directs users to plan mode for implementation. Handles both repo-level (MCP servers, agents, templates) and project-level issues.
Helps researchers stay on track with project management: phase tracking, milestone and task management, progress briefs for colleagues and supervisors, decision logging, meeting notes, and timeline management.
Manages versioning, changelogs, backups, and releases for the RWA codebase. Guides the user through creating a new CalVer release with local backup, environment snapshot, changelog updates, git tagging, and GitHub push.
Orchestrates end-to-end research workflows across specialist agents, manages stage-by-stage handoffs, and keeps workflow state visible so researchers always know the next step.
Helps plan and design research projects at the outset. Guides protocol development, study registration, ethics applications, grant writing, and study design selection.
Guides first-time users through the complete setup of the Research Workflow Assistant (RWA): prerequisites, Python environment, MCP server installation, API key configuration and validation, project folder setup, and optional first project creation.
Diagnoses and resolves RWA environment, configuration, and MCP server issues. Handles missing tools, API key failures, interpreter and venv problems, startup issues, and day-to-day how-to questions.
Co-develops human-friendly, LLM-executable verification workbooks, tracks verifier preferences, and maintains reproducibility evidence across research workflows.