
papersgpt-for-zotero
A powerful Zotero AI and MCP plugin with ChatGPT, Gemini, Claude, Grok, DeepSeek, OpenRouter, Kimi, GLM, SiliconFlow, GPT-oss, Gemma 3, Qwen 3
Stars: 1868

PapersGPT For Zotero is an AI plugin that enhances papers reading and research efficiency by integrating cutting-edge LLMs and offering seamless Zotero integration. Users can ask questions, extract insights, and converse with PDFs directly, making it a powerful research assistant for scholars, researchers, and anyone dealing with large amounts of text in PDF format. The plugin ensures privacy and data safety by using locally stored models and modules, with the ability to switch between different models easily. It provides a user-friendly interface for managing and chatting documents within Zotero, making research tasks more streamlined and productive.
README:
PapersGPT is a Zotero plugin that brings state-of-the-art Zotero AI capabilities directly into your research workflow, allowing you to chat PDFs in Zotero, quickly gain key detailed insight, generate summaries, and more. It supports GPT 5, Gemini, DeepSeek V3.1, Grok 4, ChatGPT, o1/o3/o4-mini, Claude, OpenRouter, SiliconFlow, gpt-oss, Kimi K2, GLM 4.5, DeepSeek R1 0528, Qwen3, Gemma 3, Llama 3.2 and Mistral.
Now PapersGPT supports MCP β¨ π₯, any chatbot client which supports MCP can connect to your personal Zotero library through PapersGPT.
- First, download the latest PapersGPT.
- Then, install the downloaded Zotero plugin file. For more details, please see here.
-
Chat with a Single PDF
-
Chat with Multiple PDFs
- Select multiple files or a collection in the main Zotero window. Hold
Ctrl
while clicking files on Windows. HoldCommand
while clicking files on Mac. You can see the demo below.
- Select multiple files or a collection in the main Zotero window. Hold
2. Select a LLM model and configure the API KEY of the model, more detailed information please see here
- Use the built-in prompts for common tasks like: Summary, Background, Generating a literature review, Theoretical frameworks, Future directions.
- You can also directly type any question or custom prompt to start the conversation.
-
After chatting, you can easily save the key insights and answers you've gathered from the conversation.
-
When you're finished, click the red cross (X) close button to exit the PapersGPT window.
The fastest responding MCP server connecting to Zotero
C++ MCP server, no need to install Python or Node, after installing the PapersGPT plugin, start Zotero, and it can be used on all Chatbot clients that support MCP Server on Mac and Windows. It supports BM25 full-text search of document title, author, tags, abstract, notes, annotation and collection.
Please use SSE Server of MCP in the MCP host(such as ChatWise, Cherry Studio, Cursor or Gemini Cli...), set the URL to http://localhost:9080/sse
Blazing-Fast. Even for 100+ Page Documents
Optimized for heavy documents, 5x faster PDF reading, allowing you to glide through hundred-page reports, academic papers, and e-books with zero lag.
Chat multiple PDFs
https://github.com/user-attachments/assets/a7c383cd-3986-44cb-bd0e-0d4832b07500
Lots of SOTA Business LLMs For Choosing:
- The offical API of Qwen, Mistral, Kimi, Z.ai and SiliconFlow can all be accessed in PapersGPT now, they are all top models with very high cost performance.
- Integrate OpenRouter in which there are almost all the SOTA business models, and just one key to access all the models on it.
GPT 5, Claude Opus 4.1, Grok 4, Gemini 2.5 Pro/Flash, Kimi K2, GLM 4.5, Qwen3(free), DeepSeek(free), Claude 4 are all here. β¨ π₯ - Powered by the smartest cutting-edge LLMs, offering high accuracy to assist you effectively reading papers. Now support the following latest SOTA models:
Tongyi DeepResearch 30B A3B, o4-mini-deep-research DeepResearch models β¨ π₯π₯
Grok 4 Fast Now it is free in OpenRouter
gpt-5 The latest SOTA model of OpenAI; Please note that GPT 5 needs identity checked based on OpenAI requirements β¨ π₯
gemini-2.5-pro #1 on ChatBot Arena Leaderboard; β¨ π₯
qwen3-next-80b-a3b-thinking a very fast and chip thinking model β¨ π₯
deepseek-v3.1 very chip β¨ π₯
kimi-k2-0905-preview very chip β¨ π₯
Claude-Opus-4.1 New model of Claude
qwen3
o1/o3/o4-mini
gpt-4.1
DeepSeek-V3
DeepSeek-R1
claude-3.7-sonnet
grok3
gemini-2.0-flash-thinking
gemini-2.0-pro-exp
gemini-2.0-flash-exp
gemini-2.0-flash
gmini-2.0-flash-Lite
gemini-1.5-pro
gemini-1.5-flash
chatgpt-4o-latest
gpt-4o-2024-11-20
gpt-4o-mini
claude-3.5-sonnet
claude-3.5-haiku
One click running local totaly free SOTA LLMs on Windows and Mac β¨ π₯
- Now support the following models:
gpt-oss-20b OpenAI open source model β¨ π₯ π₯
DeepSeek 0528 Distill Qwen3 8B β¨ π₯
Gemma 3 π₯
Qwen 3 π₯
Phi-4
Phi-4-Mini-Reasoning
Mistral 3.1
DeepSeek-Distill-Llama
Llama 3.2 - Models of different sizes are built in based on the size of the local machine GPU.
- Note: Please keep a good connection with huggingface and github network for models and environment downloading.
- These models can be automatically downloaded, installed and used with just one click on the plugin page, models are all locally stored, ensuring not sending your data to remote LLMs.
Of course, these models can be switched as your will, and smarter Open Source LLMs in the future would be accessed as soon as possible. - 100% Privacy and Safe of Your Personal Data. Besides local LLMs, the RAG modules of embeddings, vector database and rerank are all built and runned locally, There will be no data leakage and it can be used normally even on the plane when the internet can't be connected.
- Don't worry about your memory overflow, all the Local models shown in PapersGPT can run on your PC. If there are GPUs on your computer, it will automatically choose GPU to run local LLM instead of CPU. Recommand Gemma3 1b, DeepSeek-Distill-Qwen-1.5B or Qwen3-1.7B, in almost all the computers, they all can run and respond quickly.
https://github.com/user-attachments/assets/2630a332-1bcd-4132-a37e-d8b360ba1c09
Compatible with ollama:
- If use ollama, just choose the Ollama in the Customized selection. The model name need to fill is consistent with the name in ollama.
Seamless Zotero Integration:
- Syncs directly with your Zotero library, making it easy to manage and chat your documents without leaving the Zotero interface.
If you like to build the plugin by yourself, do as the below commands:
git clone https://github.com/papersgpt/papersgpt-for-zotero.git
cd papersgpt-for-zotero
npm install
npm run build
The plugin file(papersgpt.xpi) will be built and generated into the build directory
Research Assistance:
- Summarize research papers, identify key concepts, and quickly get answers to your questions.
Academic Writing:
- Generate insights for literature reviews or dive deep into specific sections of papers.
Collaborative Projects:
- Share annotated PDFs and responses with colleagues and teams for smoother collaboration.
Contributions to PapersGPT are welcome! Please follow the standard GitHub process for submitting pull requests or reporting issues.
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for papersgpt-for-zotero
Similar Open Source Tools

papersgpt-for-zotero
PapersGPT For Zotero is an AI plugin that enhances papers reading and research efficiency by integrating cutting-edge LLMs and offering seamless Zotero integration. Users can ask questions, extract insights, and converse with PDFs directly, making it a powerful research assistant for scholars, researchers, and anyone dealing with large amounts of text in PDF format. The plugin ensures privacy and data safety by using locally stored models and modules, with the ability to switch between different models easily. It provides a user-friendly interface for managing and chatting documents within Zotero, making research tasks more streamlined and productive.

krita-ai-diffusion
Krita-AI-Diffusion is a plugin for Krita that allows users to generate images from within the program. It offers a variety of features, including inpainting, outpainting, generating images from scratch, refining existing content, live painting, and control over image creation. The plugin is designed to fit into an interactive workflow where AI generation is used as just another tool while painting. It is meant to synergize with traditional tools and the layer stack.

LLM-Minutes-of-Meeting
LLM-Minutes-of-Meeting is a project showcasing NLP & LLM's capability to summarize long meetings and automate the task of delegating Minutes of Meeting(MoM) emails. It converts audio/video files to text, generates editable MoM, and aims to develop a real-time python web-application for meeting automation. The tool features keyword highlighting, topic tagging, export in various formats, user-friendly interface, and uses Celery for asynchronous processing. It is designed for corporate meetings, educational institutions, legal and medical fields, accessibility, and event coverage.

persian-license-plate-recognition
The Persian License Plate Recognition (PLPR) system is a state-of-the-art solution designed for detecting and recognizing Persian license plates in images and video streams. Leveraging advanced deep learning models and a user-friendly interface, it ensures reliable performance across different scenarios. The system offers advanced detection using YOLOv5 models, precise recognition of Persian characters, real-time processing capabilities, and a user-friendly GUI. It is well-suited for applications in traffic monitoring, automated vehicle identification, and similar fields. The system's architecture includes modules for resident management, entrance management, and a detailed flowchart explaining the process from system initialization to displaying results in the GUI. Hardware requirements include an Intel Core i5 processor, 8 GB RAM, a dedicated GPU with at least 4 GB VRAM, and an SSD with 20 GB of free space. The system can be installed by cloning the repository and installing required Python packages. Users can customize the video source for processing and run the application to upload and process images or video streams. The system's GUI allows for parameter adjustments to optimize performance, and the Wiki provides in-depth information on the system's architecture and model training.

magpie
This is the official repository for 'Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing'. Magpie is a tool designed to synthesize high-quality instruction data at scale by extracting it directly from an aligned Large Language Models (LLMs). It aims to democratize AI by generating large-scale alignment data and enhancing the transparency of model alignment processes. Magpie has been tested on various model families and can be used to fine-tune models for improved performance on alignment benchmarks such as AlpacaEval, ArenaHard, and WildBench.

oreilly-retrieval-augmented-gen-ai
This repository focuses on Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs). It provides code and resources to augment LLMs with real-time data for dynamic, context-aware applications. The content covers topics such as semantic search, fine-tuning embeddings, building RAG chatbots, evaluating LLMs, and using knowledge graphs in RAG. Prerequisites include Python skills, knowledge of machine learning and LLMs, and introductory experience with NLP and AI models.

nextpy
Nextpy is a cutting-edge software development framework optimized for AI-based code generation. It provides guardrails for defining AI system boundaries, structured outputs for prompt engineering, a powerful prompt engine for efficient processing, better AI generations with precise output control, modularity for multiplatform and extensible usage, developer-first approach for transferable knowledge, and containerized & scalable deployment options. It offers 4-10x faster performance compared to Streamlit apps, with a focus on cooperation within the open-source community and integration of key components from various projects.

project-lakechain
Project Lakechain is a cloud-native, AI-powered framework for building document processing pipelines on AWS. It provides a composable API with built-in middlewares for common tasks, scalable architecture, cost efficiency, GPU and CPU support, and the ability to create custom transform middlewares. With ready-made examples and emphasis on modularity, Lakechain simplifies the deployment of scalable document pipelines for tasks like metadata extraction, NLP analysis, text summarization, translations, audio transcriptions, computer vision, and more.

flow-like
Flow-Like is an enterprise-grade workflow operating system built upon Rust for uncompromising performance, efficiency, and code safety. It offers a modular frontend for apps, a rich set of events, a node catalog, a powerful no-code workflow IDE, and tools to manage teams, templates, and projects within organizations. With typed workflows, users can create complex, large-scale workflows with clear data origins, transformations, and contracts. Flow-Like is designed to automate any process through seamless integration of LLM, ML-based, and deterministic decision-making instances.

PrivateDocBot
PrivateDocBot is a local LLM-powered chatbot designed for secure document interactions. It seamlessly merges Chainlit user-friendly interface with localized language models, tailored for sensitive data. The project streamlines data access by deciphering intricate user guides and extracting vital insights from complex PDF reports. Equipped with advanced technology, it offers an engaging conversational experience, redefining data interaction and empowering users with control.

AiTextDetectionBypass
ParaGenie is a script designed to automate the process of paraphrasing articles using the undetectable.ai platform. It allows users to convert lengthy content into unique paraphrased versions by splitting the input text into manageable chunks and processing each chunk individually. The script offers features such as automated paraphrasing, multi-file support for TXT, DOCX, and PDF formats, customizable chunk splitting methods, Gmail-based registration for seamless paraphrasing, purpose-specific writing support, readability level customization, anonymity features for user privacy, error handling and recovery, and output management for easy access and organization of paraphrased content.

amurex
Amurex is a powerful AI meeting assistant that integrates seamlessly into your workflow. It ensures you never miss details, stay on top of action items, and make meetings more productive. With real-time suggestions, smart summaries, and follow-up emails, Amurex acts as your personal copilot. It is open-source, transparent, secure, and privacy-focused, providing a seamless AI-driven experience to take control of your meetings and focus on what truly matters.

FrugalGPT
FrugalGPT is a framework that offers techniques for building Large Language Model (LLM) applications with budget constraints. It provides a cost-effective solution for utilizing LLMs while maintaining performance. The framework includes support for various models and offers resources for reducing costs and improving efficiency in LLM applications.

stride-gpt
STRIDE GPT is an AI-powered threat modelling tool that leverages Large Language Models (LLMs) to generate threat models and attack trees for a given application based on the STRIDE methodology. Users provide application details, such as the application type, authentication methods, and whether the application is internet-facing or processes sensitive data. The model then generates its output based on the provided information. It features a simple and user-friendly interface, supports multi-modal threat modelling, generates attack trees, suggests possible mitigations for identified threats, and does not store application details. STRIDE GPT can be accessed via OpenAI API, Azure OpenAI Service, Google AI API, or Mistral API. It is available as a Docker container image for easy deployment.

miniLLMFlow
Mini LLM Flow is a 100-line minimalist LLM framework designed for agents, task decomposition, RAG, etc. It aims to be the framework used by LLMs, focusing on high-level programming paradigms while stripping away low-level implementation details. It serves as a learning resource and allows LLMs to design, build, and maintain projects themselves.

fridon-ai
FridonAI is an open-source project offering AI-powered tools for cryptocurrency analysis and blockchain operations. It includes modules like FridonAnalytics for price analysis, FridonSearch for technical indicators, FridonNotifier for custom alerts, FridonBlockchain for blockchain operations, and FridonChat as a unified chat interface. The platform empowers users to create custom AI chatbots, access crypto tools, and interact effortlessly through chat. The core functionality is modular, with plugins, tools, and utilities for easy extension and development. FridonAI implements a scoring system to assess user interactions and incentivize engagement. The application uses Redis extensively for communication and includes a Nest.js backend for system operations.
For similar tasks

rag-chatbot
rag-chatbot is a tool that allows users to chat with multiple PDFs using Ollama and LlamaIndex. It provides an easy setup for running on local machines or Kaggle notebooks. Users can leverage models from Huggingface and Ollama, process multiple PDF inputs, and chat in multiple languages. The tool offers a simple UI with Gradio, supporting chat with history and QA modes. Setup instructions are provided for both Kaggle and local environments, including installation steps for Docker, Ollama, Ngrok, and the rag_chatbot package. Users can run the tool locally and access it via a web interface. Future enhancements include adding evaluation, better embedding models, knowledge graph support, improved document processing, MLX model integration, and Corrective RAG.

pdftochat
PDFToChat is a tool that allows users to chat with their PDF documents in seconds. It is powered by Together AI and Pinecone, utilizing a tech stack including Next.js, Mixtral, M2 Bert, LangChain.js, MongoDB Atlas, Bytescale, Vercel, Clerk, and Tailwind CSS. Users can deploy the tool to Vercel or any other host by setting up Together.ai, MongoDB Atlas database, Bytescale, Clerk, and Vercel. The tool enables users to interact with PDFs through chat, with future tasks including adding features like trash icon for deleting PDFs, exploring different embedding models, implementing auto scrolling, improving replies, benchmarking accuracy, researching chunking and retrieval best practices, adding demo video, upgrading to Next.js 14, adding analytics, customizing tailwind prose, saving chats in postgres DB, compressing large PDFs, implementing custom uploader, session tracking, error handling, and support for images in PDFs.

END-TO-END-GENERATIVE-AI-PROJECTS
The 'END TO END GENERATIVE AI PROJECTS' repository is a collection of awesome industry projects utilizing Large Language Models (LLM) for various tasks such as chat applications with PDFs, image to speech generation, video transcribing and summarizing, resume tracking, text to SQL conversion, invoice extraction, medical chatbot, financial stock analysis, and more. The projects showcase the deployment of LLM models like Google Gemini Pro, HuggingFace Models, OpenAI GPT, and technologies such as Langchain, Streamlit, LLaMA2, LLaMAindex, and more. The repository aims to provide end-to-end solutions for different AI applications.

llama-index
This repository, llama-index, contains a collection of apps powered by LlamaIndex. LlamaIndex is an open-source project that provides a simple interface between LLMs and external data sources like APIs, PDFs, SQL etc. It provides indices over structured and unstructured data, helping to abstract away the differences across data sources. The repository includes apps like chat-with-pdf and summarize-url, showcasing the capabilities of LlamaIndex in interacting with PDFs and summarizing URLs.

papersgpt-for-zotero
PapersGPT For Zotero is an AI plugin that enhances papers reading and research efficiency by integrating cutting-edge LLMs and offering seamless Zotero integration. Users can ask questions, extract insights, and converse with PDFs directly, making it a powerful research assistant for scholars, researchers, and anyone dealing with large amounts of text in PDF format. The plugin ensures privacy and data safety by using locally stored models and modules, with the ability to switch between different models easily. It provides a user-friendly interface for managing and chatting documents within Zotero, making research tasks more streamlined and productive.

examples
This repository contains a collection of sample applications and Jupyter Notebooks for hands-on experience with Pinecone vector databases and common AI patterns, tools, and algorithms. It includes production-ready examples for review and support, as well as learning-optimized examples for exploring AI techniques and building applications. Users can contribute, provide feedback, and collaborate to improve the resource.

OpenAGI
OpenAGI is an AI agent creation package designed for researchers and developers to create intelligent agents using advanced machine learning techniques. The package provides tools and resources for building and training AI models, enabling users to develop sophisticated AI applications. With a focus on collaboration and community engagement, OpenAGI aims to facilitate the integration of AI technologies into various domains, fostering innovation and knowledge sharing among experts and enthusiasts.

sirji
Sirji is an agentic AI framework for software development where various AI agents collaborate via a messaging protocol to solve software problems. It uses standard or user-generated recipes to list tasks and tips for problem-solving. Agents in Sirji are modular AI components that perform specific tasks based on custom pseudo code. The framework is currently implemented as a Visual Studio Code extension, providing an interactive chat interface for problem submission and feedback. Sirji sets up local or remote development environments by installing dependencies and executing generated code.
For similar jobs

SLR-FC
This repository provides a comprehensive collection of AI tools and resources to enhance literature reviews. It includes a curated list of AI tools for various tasks, such as identifying research gaps, discovering relevant papers, visualizing paper content, and summarizing text. Additionally, the repository offers materials on generative AI, effective prompts, copywriting, image creation, and showcases of AI capabilities. By leveraging these tools and resources, researchers can streamline their literature review process, gain deeper insights from scholarly literature, and improve the quality of their research outputs.

paper-ai
Paper-ai is a tool that helps you write papers using artificial intelligence. It provides features such as AI writing assistance, reference searching, and editing and formatting tools. With Paper-ai, you can quickly and easily create high-quality papers.

paper-qa
PaperQA is a minimal package for question and answering from PDFs or text files, providing very good answers with in-text citations. It uses OpenAI Embeddings to embed and search documents, and follows a process of embedding docs and queries, searching for top passages, creating summaries, scoring and selecting relevant summaries, putting summaries into prompt, and generating answers. Users can customize prompts and use various models for embeddings and LLMs. The tool can be used asynchronously and supports adding documents from paths, files, or URLs.

ChatData
ChatData is a robust chat-with-documents application designed to extract information and provide answers by querying the MyScale free knowledge base or uploaded documents. It leverages the Retrieval Augmented Generation (RAG) framework, millions of Wikipedia pages, and arXiv papers. Features include self-querying retriever, VectorSQL, session management, and building a personalized knowledge base. Users can effortlessly navigate vast data, explore academic papers, and research documents. ChatData empowers researchers, students, and knowledge enthusiasts to unlock the true potential of information retrieval.

noScribe
noScribe is an AI-based software designed for automated audio transcription, specifically tailored for transcribing interviews for qualitative social research or journalistic purposes. It is a free and open-source tool that runs locally on the user's computer, ensuring data privacy. The software can differentiate between speakers and supports transcription in 99 languages. It includes a user-friendly editor for reviewing and correcting transcripts. Developed by Kai DrΓΆge, a PhD in sociology with a background in computer science, noScribe aims to streamline the transcription process and enhance the efficiency of qualitative analysis.

AIStudyAssistant
AI Study Assistant is an app designed to enhance learning experience and boost academic performance. It serves as a personal tutor, lecture summarizer, writer, and question generator powered by Google PaLM 2. Features include interacting with an AI chatbot, summarizing lectures, generating essays, and creating practice questions. The app is built using 100% Kotlin, Jetpack Compose, Clean Architecture, and MVVM design pattern, with technologies like Ktor, Room DB, Hilt, and Kotlin coroutines. AI Study Assistant aims to provide comprehensive AI-powered assistance for students in various academic tasks.

data-to-paper
Data-to-paper is an AI-driven framework designed to guide users through the process of conducting end-to-end scientific research, starting from raw data to the creation of comprehensive and human-verifiable research papers. The framework leverages a combination of LLM and rule-based agents to assist in tasks such as hypothesis generation, literature search, data analysis, result interpretation, and paper writing. It aims to accelerate research while maintaining key scientific values like transparency, traceability, and verifiability. The framework is field-agnostic, supports both open-goal and fixed-goal research, creates data-chained manuscripts, involves human-in-the-loop interaction, and allows for transparent replay of the research process.

k2
K2 (GeoLLaMA) is a large language model for geoscience, trained on geoscience literature and fine-tuned with knowledge-intensive instruction data. It outperforms baseline models on objective and subjective tasks. The repository provides K2 weights, core data of GeoSignal, GeoBench benchmark, and code for further pretraining and instruction tuning. The model is available on Hugging Face for use. The project aims to create larger and more powerful geoscience language models in the future.