Evidence Synthesis Python Packages

scibraid

Turns a research question into a graph of hypotheses, experiments, conditions and results, built by a coding agent from the papers. Every link carries a verbatim quote checked against the source text. Graphs for different questions are pooled and aligned to surface connections no single review was looking for. No API keys, no server.

citevahti

Run unit tests on your manuscript. Check every manuscript claim against its cited evidence. Human-first, AI-second, Zotero-audited, local-first.

scienceai-llm

An open-source agentic harness for scientific literature analysis. Coordinates frontier models to extract data, replicate findings, and perform systematic reviews with full provenance tracking.

living-review-updater

Keep a systematic review up to date: rank/flag newly-found studies using your own prior screening decisions. Ranks for human review, never auto-excludes.

deduplicate-it

Simple online deduplication of literature search results using DOI and title

okf-loremaster

Multi-agentic biomedical literature evidence extraction, curation, and summarization from PubMed/PMC in Open Knowledge Format (OKF) for downstream machine learning, feature selection, and agentic applications.

destiny-deduper

A suite of tools for deduplicating citations.

sievesafe

Zero-shot title/abstract screening for systematic reviews that auto-excludes only below a pre-specified threshold

reproweave

Local-first evidence maps and replication triage for engineering and AI papers.

vahtian

Citation-true research synthesis with Zotero, PubMed intake, provenance tracking, and blinded human–AI dual-rating records.

helix-mcp

Clinical evidence synthesis engine. Scored, explainable access to ClinicalTrials.gov, PubMed, and openFDA in a single API call. REST + MCP server. No API key required.

metascreener-lars-ulaval

metaScreener — a plugin-based desktop application for human-in-the-loop systematic literature screening. Combines deterministic heuristic filters with LLM inference in a sequential, auditable pipeline. SHA-256 verified bundles for full reproducibility. MIT licensed.