littlelelephant GitHub avatar

literature-review-agent

littlelelephant

An auditable, resumable AI workflow that searches scholarly literature via Europe PMC and arXiv, screens and deduplicates records, and writes evidence-grounded literature reviews using LangGraph agents.

Stars

7

7-day growth

No data

Forks

0

Open issues

0

License

AGPL-3.0

Last updated

2026-07-31

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It bridges literature retrieval and review with a transparent, auditable pipeline that explicitly labels evidence depth, supports interactive outline approval and resumption, and combines two specialized LangGraph agents.

Who it is for

  • Researchers and systematic reviewers who need reproducible literature searches
  • AI/ML engineers evaluating retrieval-augmented generation evidence
  • Technical writers or analysts producing evidence-grounded reviews
  • Open-source developers contributing to scientific AI workflows

Use cases

  • Searching Europe PMC and arXiv on a topic and exporting a deduplicated CSV
  • Generating an evidence-informed outline and writing an abstract-grounded literature review
  • Running a full-text review from local PDF or Markdown documents with the Review Agent
  • Recovering or adjusting a session with feedback before approval

Strengths

  • Combines two LangGraph agents for retrieval and review in one workflow
  • Uses official Europe PMC and arXiv APIs with bounded one-hop citation expansion
  • Explicitly labels abstract-level vs full-text findings
  • Resumable sessions and audit artifacts support transparency

Considerations

  • Default model requires DEEPSEEK_API_KEY and .env is not automatically loaded
  • Combined abstract pipeline does not read full text; full-text review requires separate local documents
  • Requires Python 3.11+ and setup via scripts; AGPL-3.0 license may limit some reuse

README quick start

Quick start

Description

A LangGraph-powered agent for literature search, evidence screening, outline generation, and evidence-grounded review writing.

Related repositories

Similar projects matched by category, topics, and programming language.

makecindy
Featured
makecindy GitHub avatar

cindy

Cindy is an open-source AI agent that runs locally on your machine, integrates multiple AI harnesses and models, and provides memory, skills, and automation to perform real work in your projects and apps.

AI & Machine LearningLarge Language Models
958
uzairansaruzi
Featured
uzairansaruzi GitHub avatar

hermex

Hermex is a native SwiftUI iPhone app that lets you control a self-hosted Hermes AI agent directly from your phone, with no subscriptions, tracking, or third-party relay.

AI & Machine LearningLarge Language Models
941
hahhforest
Featured
hahhforest GitHub avatar

pi-textbook

A hands-on course that walks through building a Pi-style coding agent from scratch across 15 checkpoints, starting from an offline agent trajectory.

AI & Machine LearningLarge Language Models
625