The Controllable RAG Agent framework provides a modular approach to building Retrieval-Augmented Generation systems. It allows you to configure and chain retrieval components, memory modules, and generation strategies. Developers can plug in different LLMs, vector databases, and policy controllers to adjust how documents are fetched and processed before generation. Built on Python, it includes utilities for indexing, querying, conversation history tracking, and action-based control flows, making it ideal for chatbots, knowledge assistants, and research tools.

Faraday Web Researcher Agent leverages AI and web scraping techniques to perform end-to-end online research workflows. This agent integrates with various search engines and content sources, automatically querying topics, crawling result pages, and extracting relevant content. It processes HTML and PDF documents, filters extraneous details, and applies natural language processing to generate concise summaries or structured reports. Users can customize search parameters, set depth of research, and define output formats, enabling tailored intelligence gathering for market analysis, academic studies, or competitive intelligence. By automating repetitive tasks, Faraday accelerates research cycles, reduces human error, and provides a unified interface for accessing and digesting large volumes of web-based information.

MARL-DPP is an open-source framework enabling multi-agent reinforcement learning (MARL) with enforced diversity through Determinantal Point Processes (DPP). Traditional MARL approaches often suffer from policy convergence to similar behaviors; MARL-DPP addresses this by incorporating DPP-based measures to encourage agents to maintain diverse action distributions. The toolkit provides modular code for embedding DPP in training objectives, sampling policies, and managing exploration. It includes ready-to-use integration with standard OpenAI Gym environments and the Multi-Agent Particle Environment (MPE), along with utilities for hyperparameter management, logging, and visualization of diversity metrics. Researchers can evaluate the impact of diversity constraints on cooperative tasks, resource allocation, and competitive games. The extensible design supports custom environments and advanced algorithms, facilitating exploration of novel MARL-DPP variants.

MineLand provides a flexible 3D sandbox environment inspired by Minecraft for training reinforcement learning agents. It features Gym-compatible APIs for seamless integration with existing RL libraries such as Stable Baselines, RLlib, and custom implementations. Users gain access to a library of tasks, including resource collection, navigation, and construction challenges, each with configurable difficulty and reward structures. Real-time rendering, multi-agent scenarios, and headless modes allow for scalable training and benchmarking. Developers can design new maps, define custom reward functions, and plugin additional sensors or controls. MineLand’s open-source codebase fosters reproducible research, collaborative development, and rapid prototyping of AI agents in complex virtual worlds.

Multi-Agent AI Researcher provides a modular, extensible framework where users can configure and deploy multiple AI agents to collaboratively tackle complex scientific inquiries. It includes a hypothesis generation agent that proposes research directions based on literature analysis, an experiment simulation agent that models and tests hypotheses, a data analysis agent that processes simulation outputs, and a drafting agent that compiles findings into structured research documents. With plugin support, users can incorporate custom models and data sources. The orchestrator manages agent interactions, logging each step for traceability. Ideal for automating repetitive tasks and accelerating R&D workflows, it ensures reproducibility and scalability across diverse research domains.

OpenPlayground is an open-source platform that allows users to experiment with and compare different large language models (LLMs). It's designed to help users understand the strengths and weaknesses of various LLMs by providing a user-friendly and interactive environment. The platform can be particularly useful for developers, researchers, and anyone interested in the capabilities of artificial intelligence. Users can sign up easily using their Google account or email.

Promethia by Soaring Titan orchestrates specialized AI agent teams that autonomously manage complex research tasks. It goes beyond traditional research tools by synthesizing insights rather than just compiling links or simple responses. Promethia leverages cutting-edge large language models and continues to evolve, integrating new analytics and data sources. This tool excels at in-depth web research today and is poised to expand its capabilities with future advancements, offering comprehensive reports that turn raw data into strategic insights.

ResearchGOAT is a generative AI-powered qualitative research platform that automates research processes, including real-time, live qualitative interviews in any language. By leveraging cutting-edge AI, ResearchGOAT captures the richness and nuance akin to human moderation. This platform is ideal for research professionals looking to simplify and enhance their qualitative research, making it easier, faster, and more affordable while maintaining high-quality insights.

Role AI is an innovative chat platform designed to facilitate engaging and unlimited AI-driven conversations. Users can communicate with different AI personalities, ranging from historical figures to fictional characters. The platform is built to provide a seamless user experience, leveraging advanced natural language processing techniques to simulate realistic interactions. Whether for entertainment, education, or research, Role AI aims to bring AI interactions closer to everyday life.

Wayfound leverages advanced AI algorithms to assist users in conducting thorough research effortlessly. It automates the collection and synthesis of information from various sources, enabling users to focus on analysis and decision-making. Whether you are conducting academic research, market analysis, or simply seeking reliable information, Wayfound streamlines the entire process, saving valuable time and improving overall productivity.

Wren is a Python-based AI agent framework designed to help developers create, manage, and deploy autonomous agents. It provides abstractions for defining tools (APIs or functions), memory stores for context retention, and orchestration logic to handle multi-step reasoning. With Wren, you can rapidly prototype chatbots, task automation scripts, and research assistants by composing LLM calls, registering custom tools, and persisting conversation history. Its modular design and callback capabilities make it easy to extend and integrate with existing applications.

Andi is the next-generation search engine that leverages generative AI technology to provide users with quick, accurate answers instead of standard search results. Unlike traditional search engines, Andi prioritizes user-friendly interactions and delivers real-time information tailored to your needs. This AI chat assistant is designed to enhance your searching experience by helping you find relevant answers, generate content, and improve information retrieval without the clutter of ads or unnecessary data, making it an indispensable tool for efficient online searches.

Character.AI Data Donation Tool is a browser extension that facilitates the collection of chat history from Character.AI. This data is used for research purposes to enhance and develop AI technology. The extension is designed with privacy in mind, ensuring that data is not sold to third parties or used for purposes outside its core functionality. The collected data helps researchers at institutions like Stanford University and others to gather insights and make advancements in the field of AI.

Desklib utilizes advanced AI algorithms to enable users to search, borrow, and share academic papers, research materials, and project documents seamlessly. It enhances the learning experience by providing easy access to quality resources, allowing users to find relevant information quickly and effectively, whether for study purposes or professional development.

Mean-Field MARL provides a robust Python framework for implementing and evaluating mean-field multi-agent reinforcement learning algorithms. It approximates large-scale agent interactions by modeling the average effect of neighboring agents via mean-field Q-learning. The library includes environment wrappers, agent policy modules, training loops, and evaluation metrics, enabling scalable training across hundreds of agents. Built on PyTorch for GPU acceleration, it supports customizable environments like Particle World and Gridworld. Modular design allows easy extension with new algorithms, while built-in logging and Matplotlib-based visualization tools track rewards, loss curves, and mean-field distributions. Example scripts and documentation guide users through setup, experiment configuration, and result analysis, making it ideal for both research and prototyping of large-scale multi-agent systems.

Pacman AI offers a fully functional Python-based environment and agent framework for the classic Pacman game. The project implements key reinforcement learning algorithms—Q-learning and value iteration—to allow the agent to learn optimal policies for pill collection, maze navigation, and ghost avoidance. Users can define custom reward functions and adjust hyperparameters such as learning rate, discount factor, and exploration strategy. The framework supports metric logging, performance visualization, and reproducible experiment setups. It is designed for easy extension, letting researchers and students integrate new algorithms or neural network-based learning approaches and benchmark them against baseline grid-based methods within the Pacman domain.

Paperguide is an AI-enhanced research platform that offers tools for managing and navigating through academic papers effortlessly. Users can conduct advanced searches across extensive databases, generate concise summaries of documents, and engage in real-time chat with PDFs. The platform also supports note-taking, annotation, and organization of references, making it an essential tool for researchers, students, and educators looking to optimize their literature reviews and writing processes.

Pentago Swap AI Agent implements an intelligent opponent for the Pentago Swap game by leveraging a Monte Carlo Tree Search (MCTS) algorithm to explore and evaluate potential game states. At each turn, the agent simulates numerous playouts, scoring resulting board positions to identify moves that maximize win probability. It supports customization of search parameters like simulation count, exploration constant, and playout policy, enabling users to fine-tune performance. The agent includes a command-line interface for head-to-head matches, self-play to generate training data, and a Python API for integration into larger game environments or tournaments. Built with modular code, it facilitates extension with alternative heuristics or neural network evaluators for advanced research and development.

Rayyan is a sophisticated AI-assisted platform tailored for researchers to streamline the process of conducting systematic reviews and literature reviews. The platform offers powerful tools for collaboration, enabling users to import references, screen studies, and organize findings. With Rayyan, researchers can work on reviews both individually and in teams, providing seamless integration, remote accessibility, and a user-friendly interface designed to optimize productivity and accuracy in academic and biomedical research.

Research Navigator is an AI-driven tool that automates literature review tasks for researchers, students, and professionals. Leveraging advanced NLP and knowledge graph technologies, it retrieves and filters relevant scientific articles based on user-defined queries. It extracts salient points, methodologies, and results to generate concise summaries, highlights differences across studies, and provides side-by-side comparisons. The platform supports citation export in multiple formats and integrates with existing documentation workflows via API or CLI. With customizable search parameters, users can focus on specific domains, publication years, or keywords. The agent also maintains session-based memory, enabling follow-up queries and incremental refinement of research topics.