Projects sharing features with PaperBanana

This project is a scientific agent framework and workflow orchestrator designed to extend large language models with specialized tools for genomic, chemical, and biological research. It provides a system for planning research hypotheses and executing automated workflows by integrating scientific databases with dynamic code execution. The framework includes a cheminformatics modeling suite for predicting molecular bioactivity and performing virtual screening, alongside a bioinformatics analysis toolkit for processing genomic sequences and single-cell data. It also features an academic document

Paper2Poster is an automated system designed to convert dense academic research papers into professional, branded presentation posters. By utilizing large language models, the tool extracts key findings and structured data from scientific documents, which are then mapped into predefined visual grids to create editable presentation layouts. The system distinguishes itself through a multi-agent orchestration framework that coordinates specialized tasks, including content summarization, visual asset placement, and quality verification. Users can define visual aesthetics and institutional brandin

PPTAgent is an agentic AI framework designed to research, design, and generate presentation slides from prompts or documents using large language models. It functions as an automated research agent and PowerPoint generator that coordinates autonomous workflows to produce structured presentation decks. The system employs a research-first planning phase to gather comprehensive information and determine content structure before moving to production. It distinguishes itself through a reflective iterative workflow where the agent reviews and refines slides, as well as an integrated text-to-image a

This project is an automated content automation pipeline and AI article generator. It uses large language models to research topics from diverse web sources and academic repositories to generate evidence-based text and accompanying AI imagery for digital publishing. The system features a centralized social media management dashboard used to coordinate posting schedules, tone, and account positioning across multiple platforms. It employs a vector-based deduplicator to identify and remove redundant stories from the pipeline and uses topic clustering to rank content based on relevance. The work

FriendsDontLetFriends is a scientific data visualization guide and framework designed to help users create accurate plots while avoiding common data representation mistakes. It provides a collection of scripts and guidelines for selecting distribution plots, color scales, and layouts that accurately represent complex experimental data. The project distinguishes itself through specialized toolkits for revealing hidden patterns in large datasets. It includes systems for heatmap optimization via dimension reordering and outlier management, as well as spatial layout algorithms to improve the inte

Nature-skills is a suite of specialized software components designed for academic writing assistance, literature retrieval, document conversion, peer review simulation, and scientific figure generation. It functions as an LLM-driven assistant to help researchers polish scientific manuscripts, manage bibliographic references, and produce publication-quality materials for high-impact journals. The project distinguishes itself through a multi-stage writing pipeline and an agentic literature retrieval system that verifies citations across academic databases. It includes capabilities for convertin

ml-visuals is a machine learning figure library and research asset repository containing reusable scientific diagrams and visual templates. It provides a modular system of graphical primitives and layout templates designed to standardize the visual representation of machine learning concepts and architectures. The project utilizes a schema-driven illustration system that defines visual elements and spatial relationships using structured data to ensure reproducible scientific figures. This framework allows for the creation of professional diagrams and charts for academic papers and technical p

huashu-design is a design system infrastructure and a set of specialized design engines for high-fidelity HTML prototyping, quality evaluation, and presentation conversion. It provides tools for generating interactive single-file HTML mockups, frame-based motion design, and a visual evaluator that analyzes design quality across five dimensions using radar charts. The system distinguishes itself through a translation pipeline that converts HTML slide decks into editable PowerPoint and PDF objects rather than flat images. It includes a motion design engine that uses a time-slice model to render

AG2 is a multi-agent large language model orchestration framework, agentic workflow automation tool, and RAG-enabled agent platform. It functions as a communication protocol and framework for coordinating multiple AI agents to solve complex tasks through shared state and standardized messaging. The project distinguishes itself through flexible coordination strategies, including hierarchical agent organization, hub-and-spoke models, and dynamic routing that analyzes conversation context to distribute work. It implements multi-stage feedback loops for iterative refinement and uses schema-constr

This project is an AI research tool designed for autonomous web information gathering and automated topic research. It utilizes agent orchestration to combine search engines and web scraping, enabling the system to discover detailed information and build a comprehensive understanding of complex subjects without manual step-by-step guidance. The tool employs an iterative research execution model that recursively generates targeted search queries and refines directions based on previous results. It includes a feedback loop that compares current findings against initial objectives to identify kn

Makie.jl is a high-performance Julia data visualization library and hardware-accelerated plotting engine used to create interactive 2D and 3D visualizations. It functions as a reactive visualization framework where plots update automatically via observables and compute graphs, and as a vector graphics generator for high-resolution academic output. The system is distinguished by its backend-agnostic rendering pipeline, which supports OpenGL, WebGL, and ray-traced scenes. It employs a grammar-of-graphics approach to map variables to aesthetic attributes and utilizes a hierarchical scene graph t

This project is a collection of methodological guides and standards for academic document workflows, specifically focusing on a LaTeX scientific writing guide, typesetting standards, and Python data visualization guidelines. It provides a framework for professional scientific paper typesetting and the management of technical documents. The project distinguishes itself by providing specific workflows for programmatic data visualization, including the use of Python and Matlab scripts to ensure high-quality figures and consistent styling. It also details an academic document workflow that integr

Maestro is an autonomous task workflow engine that decomposes high-level goals into hierarchical sub-tasks and orchestrates their execution using multiple language model agents. It provides a unified interface for routing requests across different LLM providers, including proprietary models like Anthropic, OpenAI, and Gemini, as well as local models, enabling flexible provider selection and switching through a single entry point. The system distinguishes itself through its ability to generate complete software project structures directly on the host machine, creating directories and source fi

Paper-qa is a retrieval augmented generation system designed for question answering and analysis of scientific literature and technical documents. It functions as an LLM-powered research assistant that extracts grounded answers and summaries with citations from a document library. The system utilizes an agentic RAG orchestrator to iteratively refine search queries and gather evidence through multi-step tool calling. It features a multimodal document parser that extracts text, tables, and images from PDFs, alongside a vector-based indexer that embeds and caches document libraries for efficient

This project is a framework for training and sampling generative models designed to produce high-quality images in few steps. It provides implementations for image generation models that transform random noise into structured visual data through an optimized sampling process. The system specializes in accelerating image generation through consistency distillation and consistency training. It includes tools to transform pre-trained diffusion models into faster versions by distilling knowledge from a teacher model into a student model, as well as methods to train consistency models from scratch

DB-GPT is an agentic data analysis platform and business intelligence AI that functions as a large language model data assistant. It provides a text-to-SQL interface and a sandboxed code execution environment to translate natural language into executable database queries and Python scripts. The platform utilizes iterative agentic reasoning to plan and execute multi-step data analysis workflows through tool calls. It features a modular skill-based extension system that allows domain knowledge and analysis workflows to be packaged into reusable functional components. The system integrates data

This project is an automated prompt engineering and optimization tool designed to iteratively create, test, and refine prompts using a language model to improve output quality. It functions as a framework for generating candidate prompts and ranking their performance through correctness matching and ELO-based ratings. The system includes capabilities for model distillation, generating high-quality example pairs from frontier models to create training data for smaller models. It also provides tools to condense prompts for smaller models and transform instruction-tuned prompts into completion-b

f3d is a fast 3D model viewer and rendering engine designed for visualizing 3D meshes, CAD files, and point clouds. It operates across multiple deployment profiles, functioning as a lightweight desktop application, a scientific data visualizer for volumetric and scalar datasets, a headless rendering engine for automated image generation, and a WebAssembly-based renderer for web applications. The project distinguishes itself through specialized support for Gaussian Splatting scene reconstructions and the ability to visualize complex scientific formats such as VTK, NetCDF, and HDF. It features

Agent-skills is a collection of structured instructions and behavioral personas designed to standardize how AI coding agents perform engineering tasks. It functions as a workflow orchestrator that maps natural language intent to repeatable technical sequences and verification checklists. The project distinguishes itself through the use of specialized markdown-defined roles, such as security auditors or test engineers, to apply targeted domain expertise. It employs an evidence-based verification model that requires runtime data or passing tests as mandatory exit criteria to ensure AI-generated

This project is a comprehensive framework for building and managing autonomous agent systems. It provides a unified architecture for orchestrating multi-agent societies, where specialized agents collaborate through roleplay to decompose and solve complex tasks. The system integrates language models with external environments, enabling agents to perform real-world actions through a standardized tool-calling abstraction layer. The framework distinguishes itself through its focus on iterative reasoning and data reliability. It employs automated feedback loops to refine agent outputs and self-eva

This project is a comprehensive AI research workflow framework and skill library designed to transform general large language models into specialized AI research agents. It provides an agentic toolset for academic writing, a knowledge base for AI engineering, and a system for analyzing research artifacts by converting documents and repositories into structured claims and evidence graphs. The framework employs a two-loop orchestration architecture to manage the research lifecycle from ideation and literature surveys to final paper drafting. It distinguishes itself through a modular skill injec

Plandex is an AI-powered software development platform that operates as a command-line interface to manage complex, long-running coding tasks. It functions as an automated agent that decomposes high-level programming objectives into granular, actionable steps, executing multi-file code changes directly within a local project environment. The system distinguishes itself through a state-machine-based execution model that tracks progress across iterative development cycles. By utilizing context-aware code indexing and an iterative feedback loop, the tool refines generated code through successive

OpenHands is an autonomous agent framework designed for software engineering workflows. It provides a modular platform for orchestrating AI agents that reason, plan, and execute tasks within isolated, containerized development environments. By integrating with standard version control and development tools, the system enables agents to autonomously navigate codebases, implement features, and resolve issues through iterative reasoning and tool execution. The platform distinguishes itself through a model-agnostic orchestrator that connects diverse language models to a unified tool registry. It

DiffSynth-Studio is a comprehensive platform for the lifecycle management of generative diffusion models, providing a unified environment for inference, fine-tuning, and training. It utilizes a modular pipeline architecture and a standardized abstraction layer to support consistent workflows across diverse model configurations for image and video generation. The platform distinguishes itself through a memory-optimized inference engine that dynamically manages resources to facilitate high-resolution generation on constrained hardware. It also integrates specialized training capabilities, inclu

This project is a research-oriented PyTorch framework designed for the implementation and training of generative video diffusion models. It provides a modular toolkit that extends standard image-based diffusion techniques into three dimensions, enabling the synthesis of coherent video sequences through iterative denoising processes. The framework distinguishes itself by utilizing factored space-time attention, which decomposes high-dimensional video data into separate spatial and temporal layers to maintain motion consistency while managing computational complexity. It supports multi-modal tr

mcp-agent is a framework for building AI agents that integrate with Model Context Protocol servers to execute tools and access data. It functions as a multi-agent orchestrator and protocol-compliant server, enabling the creation of agents that can discover and invoke tools from connected external servers. The project distinguishes itself through a durable workflow engine that supports long-running tasks capable of pausing, resuming, and surviving restarts. It implements complex orchestration patterns, including iterative evaluator-optimizer loops, hierarchical workflow nesting, and specialist

This project is a framework for developing multimodal AI agents that function as programmable participants in real-time communication rooms. It enables the construction of agents that can see, hear, and speak by integrating speech-to-text, large language models, and text-to-speech pipelines to facilitate low-latency, natural conversations. The system is distinguished by its advanced orchestration of real-time media and conversational flow, including support for full-duplex speech, preemptive response generation, and sophisticated interruption management. It further differentiates itself throu