Scholr – search 200M+ academic papers with citation-grounded synthesis
Citation-grounded synthesis beats generic RAG wrappers for academic rigor.

The product nails a focused niche: text-to-academic-figure workflows with extras like I2I editing, a multi-agent Retriever→Planner→Stylist→Visualizer→Critic pipeline, and explicit support for diagram vs. plot modes. The landing looks tidy and the mention of DDPM/ResNet and plot-code output suggests real engineering under the hood, but the space is crowded (BioRender, generalist image LLMs, fig-helpers) and model transparency, failure modes and export fidelity for journal submission are the open questions.
Researchers, PhD students, postdocs, professors, and educators who need publication-quality scientific figures
I built PaperBanana to help researchers create professional scientific figures and diagrams using AI.
It turns text descriptions or rough sketches into publication-ready illustrations, including system architectures, flowcharts, and schematics.
I’d love to hear your feedback on the output quality and what scientific styles you’d like to see added.
Citation-grounded synthesis beats generic RAG wrappers for academic rigor.
Letterboxd for academic papers fills a gap no existing platform addresses.
Generates editable scientific vectors from sketches when BioRender requires manual drag-and-drop.
BioRender already dominates this space with better scientific accuracy.
OpenAlex wrapper with a clean UI, but lacks unique discovery features.
arXiv-first paper manager with network graph viz, but Zotero already owns this space.