Enables users to conduct inspectable research with native Codex or Claude providers, producing locally saved dossiers with source-linked findings, evidence levels, falsifiers, limitations, and recorded retrieval events.
Provides local, evidence-aware research memory with human review, revision history, and an inspector, allowing assistants to preserve source reports, inferences, assumptions, and evidence across sessions.
Enables AI assistants to search Crossref for recent journal papers, ingest and bookmark verified literature, store notes and settings, and track full-text reading requests through to reports. Supports user-approved handoffs where finished reading reports become saved Markdown manuscripts, sharing one database with the web workspace.
Transforms AI assistants into research-grade cognitive workspaces with systematic reasoning, evidence-based analysis, persistent memory management, and intelligent knowledge discovery.
Enables AI agents to run reproducible systematic literature review workflows through deterministic tools for deduplication and PRISMA accounting, legal open-access PDF retrieval, corpus routing, closed-taxonomy coding, blinded inter-rater reliability, bibliography export, figure generation, manuscript synchronization, and multi-source integrity audits. It keeps research artifacts such as PDFs, Excel workbooks, BibTeX/RIS files, figures, and Word/Markdown manuscripts synchronized and audit-ready.
Enables fully local, end-to-end research automation: reproducing papers from PDF into runnable code and verified artifacts, writing papers section-by-section with LaTeX/PDF/DOCX export, and running an ideate→debate→design→verdict research pipeline—all without an API key.