Research & Education

start-llms is a comprehensive guide designed to help individuals, even those with little to no prior programming or AI knowledge, to start and improve their Large Language Model (LLM) skills. The resource aims to keep users up-to-date with the latest news and state-of-the-art techniques in the LLM field. It offers a structured learning path, including short YouTube video introductions, recommended books and articles, online courses (both free and paid options), and a strong emphasis on practical application through coding exercises. The guide also covers essential topics like prompting, Retrieval Augmented Generation (RAG), and how to find a machine learning job, making it a valuable resource for aspiring LLM experts.

PromptDen is a comprehensive platform designed for AI prompt sharing and discovery, catering to a wide range of AI models such as ChatGPT, Gemini, MidJourney, and Stable Diffusion. Users can explore, discover, and share prompts for both text and image generation. The platform fosters a community for prompt engineering, inspiration, and collaboration. Key features include PromptForge, a browser extension for ChatGPT, Claude, and Gemini, and a marketplace for buying and selling prompts and AI-generated content. PromptDen aims to boost creativity and productivity for individuals working with AI.

Podwise is an AI-powered podcast application designed to help users learn more efficiently from audio content. It offers comprehensive features such as AI-generated summaries, full transcripts, mind maps, and Q&A capabilities for millions of episodes. Users can search within 10M+ episodes, import from YouTube and RSS feeds, and even upload their own audio files for processing. The platform supports multiple languages for summaries and translations, breaking down language barriers. Podwise also integrates seamlessly with popular knowledge management tools like Notion, Readwise, Obsidian, and Logseq, allowing users to build their personal knowledge base. Available on web, iOS, and Android, it provides universal access to enhanced podcast learning.

Reflect is a beautifully minimalist note-taking application designed to mirror the way you think, now with native AI integration. It allows users to capture notes, ideas, and connections quickly, syncing them instantly across all devices. The tool features networked notes with backlinks to form a graph of ideas, creating a 'second brain' that is easily searchable. Reflect integrates AI using GPT-4 and Whisper from OpenAI to improve writing, organize thoughts, and act as an intellectual partner. Key AI capabilities include transcribing voice notes, generating article outlines, listing key takeaways from meeting notes, and chatting with notes to find and organize information. It also supports custom prompts and offers end-to-end encryption for privacy, ensuring only you can access your notes. Reflect also integrates with calendars, web clippers, and Kindle for comprehensive information management.

Sealenic is an AI-driven platform designed to revolutionize maritime operations by providing accurate, compliant, and efficient access to information. It acts as an AI agent for vessels, delivering high-confidence answers to operational questions on any device and in any language. The platform ensures data privacy and security, with all data hosted in Europe and never used for training. Sealenic seamlessly integrates with existing ERP, SMS, and DMS systems, including legacy ones, to unlock company-specific knowledge. Built for technical managers, HSEQ teams, and seafarers, it speaks the language of the maritime world, offering contextual and cited information aligned with internal rules and maritime regulations, eliminating guesswork and hallucinations. Key features include multi-format document handling, confidence scoring, role-based answers, and a secure data environment.

ForwardPath AI specializes in developing custom AI solutions and offering comprehensive AI training to empower organizations. They address common challenges businesses face in AI adoption by providing a clear path from strategy to implementation. Their services include AI Immersion Days to align teams on high-impact areas, AI Training for leveraging tools like Copilot and ChatGPT, and building enterprise-grade custom AI solutions. ForwardPath AI acts as a partner, owning recommendations through to successful deployment and optimization, ensuring long-term integration of AI into daily operations. They emphasize a practical approach, focusing on tangible business outcomes and a rapid 8-12 week deployment cycle for custom tools.

awesome-code-ai is a comprehensive list of AI coding tools, designed to assist developers with various programming tasks. The collection includes tools for code completion, intelligent assistants, and refactoring capabilities, aiming to enhance coding efficiency and productivity. While the repository is now archived, it serves as a valuable historical resource for understanding the landscape of AI-powered development tools. Developers can explore options ranging from open-source solutions like FauxPilot and TabbyML to integrated assistants within popular IDEs such as GitHub Copilot and JetBrains AI. The list also categorizes tools by function, making it easier to find specific solutions for code generation, debugging, and security analysis.

Data-Hat AI provides Orkestra, an enterprise AI agent platform specifically designed for the retail sector. It aims to plug the data-action gap by deploying AI agents that steer full-price sell-through, eliminate stock-outs, and improve margins. Orkestra's agents are pre-trained on industry-specific retail DNA, allowing for tailored solutions in apparel, luxury goods, and health & beauty. Key agents include Merchandise Planner for assortment and allocation, Replenishment Agent for inventory optimization, Demand Forecaster for multi-horizon predictions, and Pricing Optimizer for dynamic pricing. The platform emphasizes responsible AI with a "Human in the Loop" approach, offering full transparency, explainable logic, and configurable thresholds for executive approval.

Iris AI is an AI-native RFP software designed to help sales engineers, proposal writers, and presales teams automate responses to RFPs, DDQs, and security questionnaires. The platform centralizes knowledge, allowing users to build a comprehensive knowledge base by dragging and dropping Q&A pairs, past RFPs, and other relevant documents. It integrates with existing tech stacks like Salesforce, Slack, Confluence, Google Drive, and SharePoint to ensure accurate and up-to-date information. Iris AI generates first drafts in minutes, complete with inline source citations and confidence scores, significantly reducing the time spent on manual tasks and improving win rates. It also offers project management features for collaboration and task assignment, and allows for custom template export and branded deliverables.

Research Studio is an AI-enhanced platform designed to significantly speed up UX research processes. It supports over 8 file formats and 99 languages, offering unlimited, state-of-the-art transcriptions. The tool provides a canvas with draggable smart widgets for various research tasks, including extracting detailed personas, discovering user motivations with 'Jobs to Be Done', classifying user comments by sentiment, mapping user journeys, and creating user stories. It also features a competitors widget for market analysis and a questions analysis tool to enhance future investigations. An integrated AI assistant helps answer research questions, either within context or with broader knowledge. Research Studio allows for easy presentation customization and instant export to Notion, making it a comprehensive solution for UX designers, user researchers, and agencies.

localGPT is a private, on-premise Document Intelligence platform designed for secure and confidential interaction with your files. It enables users to ask questions, summarize, and uncover insights from documents using state-of-the-art AI, all while keeping data entirely on your local machine. Beyond traditional RAG, localGPT features a hybrid search engine combining semantic similarity, keyword matching, and Late Chunking for precise long-context retrieval. A smart router automatically selects between RAG and direct LLM answering, complemented by contextual enrichment and sentence-level Context Pruning. The modular, pure-Python architecture with minimal dependencies makes it easy to deploy and maintain, supporting various open-source models via Ollama and diverse embeddings.

The llm-engineer-toolkit is an open-source repository offering a meticulously curated list of over 120 Large Language Model (LLM) libraries, organized by category. This toolkit is designed to assist AI engineers and developers in efficiently discovering relevant libraries for various LLM-related tasks, including training, application development, RAG, inference, serving, data extraction, data generation, agents, evaluation, monitoring, and prompt management. It acts as a central hub for exploring tools for fine-tuning LLMs, building LLM applications, implementing Retrieval-Augmented Generation (RAG) systems, and managing LLM operations. The repository also includes related resources like LLM interview questions, prompt engineering techniques, and survey papers, making it a valuable resource for staying updated in the rapidly evolving Generative AI landscape.

LLM-Reading-List is a curated collection of academic papers primarily focused on Large Language Model (LLM) inference and model compression. This GitHub repository serves as a valuable resource for researchers and academics looking to stay updated on the latest advancements in these specialized areas of LLM development. The list is meticulously organized into categories such as Transformer Architectures, Foundation Models, Position Encoding, KV Cache, Activation, Pruning, Quantization, Normalization, Sparsity and rank compression, Fine-tuning, Sampling, Scaling, Mixture of Experts, and Watermarking. Each section provides direct links to key papers, making it an efficient way to explore foundational and cutting-edge research without extensive searching. It is particularly useful for those delving into the technical aspects of optimizing LLMs for performance and efficiency.

Anara is an AI-powered workspace designed for scientists, students, and research teams to streamline academic workflows. It enables users to search for academic papers, extract key passages, and organize their research efficiently. The tool facilitates writing with automatic citations, ensuring academic rigor by linking every insight to original sources for easy verification. Anara helps eliminate hallucinations by limiting AI responses to uploaded files and automatically finds relevant citations based on user writing. It can understand and process various file types, including dense textbooks, clinical studies, and technical research papers, providing concise, scholarly answers to questions. Additionally, Anara can generate flashcards and multiple-choice questions from uploaded materials, and allows users to build a single, searchable library for all projects, supporting both solo and collaborative work.

Skriptr is an AI-powered platform designed to enhance the research and writing process for academics and students. It leverages AI agents that collaborate with users, helping to build on insights and streamline the entire workflow from initial research to final document creation. The platform aims to improve writing quality and efficiency by providing tools that assist with various stages of academic and research writing. Skriptr focuses on making the research and writing journey more collaborative and insightful, ensuring users can produce high-quality work with greater ease.

Morphik offers AI workers designed to automate back-office functions like accounts payable, payroll, and billing for multi-site healthcare operators. The platform learns existing workflows, GL codes, and approval chains to deploy custom AI workers trained on specific operational data. These AI workers handle tasks such as reading invoices, GL coding, routing approvals, and processing payments, allowing teams to focus on vendor management and cost reduction. Morphik aims to provide complete visibility and queryability of all documents and transactions across an entire operation, leading to significant annual savings and efficient deployment within weeks. It supports multi-site skilled nursing, senior living, and general healthcare facilities.

obsidian-agent-client is an Obsidian plugin designed to bring AI agents directly into your Obsidian vault. Leveraging the Agent Client Protocol (ACP), it supports popular AI models such as Claude Code, Codex, and Gemini CLI, enabling users to interact with these agents within their notes. Key features include note mentions using `@notename` syntax, image attachments, and slash commands for agent interaction. The plugin offers multi-agent support, multi-session capabilities, and a floating chat window for quick access. Users can switch between AI models and agent modes, access session history, and export conversations as Markdown notes. It also provides terminal integration, allowing agents to execute commands and return results, and supports MCP servers without additional setup.

obsidian-smart-connections is an Obsidian plugin designed to streamline knowledge management by leveraging AI embeddings. It allows users to chat with their notes and automatically discover semantically related content, eliminating the need for manual linking and tagging. The tool supports both local embedding models for privacy and offline use, as well as integration with over 100 APIs including Claude, Gemini, ChatGPT, and Llama 3. It features a Connections view to surface relevant notes, a Lookup view for semantic search, and Pro features like inline connections and configurable scoring. The plugin is lightweight, private by design, and aims to save users time on organization, allowing more focus on creative work.

PharosBio is an AI-powered decision-support framework designed to accelerate scientific decisions in life sciences. It unifies experimental data, publications, and internal documents, transforming them into fast, reliable, and fully traceable actionable insights. The platform addresses challenges in drug development such as data silos and incomplete pipeline oversight by connecting insights from early discovery, through preclinical stages, to clinical outcomes. It supports hypothesis generation, target selection, and prioritization, and helps predict translatability of in vivo results. PharosBio emphasizes enterprise security and compliance, adhering to industry best practices for data protection, encryption, role-based access controls, and supporting certifications like GDPR, SOC2, and HIPAA.

yousan.ai is an open-source project dedicated to providing a wealth of resources for individuals studying deep learning. It encompasses a wide array of materials, including practical projects, comprehensive ebooks, and structured courses. The platform is designed to support various popular deep learning frameworks such as Caffe, TensorFlow, PyTorch, MXNet, PaddlePaddle, Darknet, Deeplearning4j, MatConvNet, Keras, Chainer, and CNTK. It covers key deep learning tasks like computer vision (image classification, segmentation, object detection), speech processing (recognition, synthesis), and natural language processing (knowledge graphs, automatic question answering). The project also offers specific resources on topics like GANs, Transformer models, and ChatGPT, making it a valuable hub for deep learning enthusiasts and professionals.

Messy Desk is a personal knowledge librarian designed to enhance learning and growth through AI assistance and social interaction. It offers a suite of features including Smart Preview, which automatically extracts key points and summaries from documents, saving users valuable time. Its Powerful Search capabilities utilize advanced semantic search to understand context and meaning, helping users find vaguely remembered documents. The tool also provides AI Explanations for complex topics and an Interactive Chat feature to get instant, context-aware answers from documents. Additionally, Messy Desk fosters community discussion, allowing users to share insights and connect with others reading the same material. It supports easy bulk uploads of PDF documents and URLs.

Simpplr is a comprehensive AI intranet and employee experience platform designed to enhance internal communications, engagement, and productivity within organizations. It goes beyond traditional intranets by integrating AI-powered features such as AI Search, which delivers trusted results across various systems, and AI Agents for employee services and support. The platform also includes Comms AI, an intelligent workspace specifically built for internal communications. Simpplr aims to keep employees informed, aligned, and productive through personalized hubs, multichannel communications, and tools for employee listening, recognition, and rewards. It is enterprise-ready with robust security and integrations, making it suitable for HR, internal communication, and IT teams across various industries.

ChatGPT AI Hub serves as a comprehensive online resource for individuals interested in ChatGPT and broader AI topics. The platform provides a variety of content, including curated ChatGPT prompts to help users get started or enhance their AI interactions. It also features tutorials and articles designed to educate users on different aspects of AI, alongside news updates to keep them informed about the latest developments in the field. Additionally, the hub offers practical tools such as a ChatGPT detector and prompt generators, aiming to assist users in both understanding and utilizing AI effectively. Downloadable ebooks are also available for those looking to deepen their knowledge of artificial intelligence.

Swiss Army Llama is a FastAPI service designed to streamline working with local LLMs by exposing convenient REST endpoints. It facilitates tasks such as obtaining text embeddings and completions using llama_cpp, and automates the process of generating embeddings for common document types like PDFs (with OCR support), Word files, and even audio files via Whisper transcription. To optimize performance, embeddings are cached in SQLite, and optional RAM Disks can be used for faster LLM loading. The service leverages a high-performance Rust-based library, fast_vector_similarity, for advanced similarity measures and supports semantic search using FAISS vector searching. It also offers multiple embedding pooling methods and a real-time application log viewer.