CityLearn provides a modular simulation platform for energy management research using reinforcement learning. Users can define multi-zone building clusters, configure HVAC systems, storage units, and renewable sources, then train RL agents against demand response events. The environment exposes state observations like temperatures, load profiles, and energy prices, while actions control setpoints and storage dispatch. A flexible reward API allows custom metrics—such as cost savings or emission reductions—and logging utilities support performance analysis. CityLearn is ideal for benchmarking, curriculum learning, and developing novel control strategies in a reproducible research framework.

Dynamic Multi-Agent RAG Pathway provides a modular architecture where each agent handles specific tasks—such as document retrieval, vector search, context summarization, or generation—while a central orchestrator dynamically routes inputs and outputs between them. Developers can define custom agents, assemble pipelines via simple configuration files, and leverage built-in logging, monitoring, and plugin support. This framework accelerates development of complex RAG-based solutions, enabling adaptive task decomposition and parallel processing to improve throughput and accuracy.

Eliza is a lightweight, open-source conversational framework that simulates a psychotherapist via pattern matching and scripted templates. Developers can define custom scripts, patterns, and memory variables to tailor responses and conversation flows. It runs in any modern browser or webview environment, supports multiple sessions, and logs interactions for analysis. Its extensible architecture allows integration into web pages, mobile apps, or desktop wrappers, making it a versatile tool for education, research, prototype development, and interactive installations.

The F1Tenth Two-Agent Simulator is a specialized simulation framework built on ROS and Gazebo to emulate two 1/10th scale autonomous vehicles racing or cooperating on custom tracks. It supports realistic tire-model physics, sensor emulation, collision detection, and data logging. Users can plug in their own planning and control algorithms, adjust agent parameters, and run head-to-head scenarios to evaluate performance, safety, and coordination strategies under controlled conditions.

Firebase GenKit is a developer framework that streamlines the creation of generative AI features using Firebase services. It includes Cloud Functions templates for invoking LLMs, Firestore triggers to log and manage prompts/responses, authentication integration, and front-end UI components for chat and content generation. Designed for serverless scalability, GenKit lets you plug in your choice of LLM provider (e.g., OpenAI) and Firebase project settings, enabling end-to-end AI workflows without heavy infrastructure management.

MultiAgentPuzzleSolver provides a modular environment where independent AI agents work together to solve puzzles such as sliding tiles, Rubik’s Cube, and logic grids. Agents share state information, negotiate subtask assignments, and apply diverse heuristics to explore the solution space more effectively than single-agent approaches. Developers can plug in new agent behaviors, customize communication protocols, and add novel puzzle definitions. The framework includes tools for real-time visualization of agent interactions, performance metrics collection, and experiment scripting. It supports Python 3.8+, standard libraries, and popular ML toolkits for seamless integration into research projects.

PromptHub is designed to streamline the process of prompt engineering for AI models. The platform offers an easy-to-use interface, robust versioning and logging capabilities, and a straightforward API. This comprehensive tool helps teams organize, test, and refine their prompts more efficiently, enabling faster iterations and better results. By eliminating the need for custom-built solutions, PromptHub allows users to focus on creativity and innovation, making it an essential tool for prompt engineers, founders, and anyone involved in AI model development.

TinyAgent is a low-code AI agent builder that allows anyone to design, test, and deploy intelligent agents. Define custom prompts, integrate external APIs or data sources, and configure agent memory to retain context. Once configured, agents can be used via a web chat interface, Chrome extension, or embed code. With analytics and logging, you can monitor performance and iterate quickly. TinyAgent streamlines repetitive tasks such as report generation, email triage, and lead qualification, reducing manual work and scaling team productivity.

MultiAgentModel provides a unified API to define custom environments and agent classes for multi-agent scenarios. Developers can specify observation and action spaces, reward structures, and communication channels. Built-in support for popular RL algorithms like PPO, DQN, and A2C allows training with minimal configuration. Real-time visualization tools help monitor agent interactions and performance metrics. The modular architecture ensures easy integration of new algorithms and custom modules. It also includes a flexible configuration system for hyperparameter tuning, logging utilities for experiment tracking, and compatibility with OpenAI Gym environments for seamless portability. Users can collaborate on shared environments and replay logged sessions for analysis.

AgentSimJS is designed to simplify the creation and execution of large-scale agent-based models in JavaScript. With its modular architecture, developers can define agents with custom states, sensors, decision-making functions, and actuators, then integrate them into dynamic environments parameterized by global variables. The framework orchestrates discrete time-step simulations, manages event-driven messaging between agents, and logs interaction data for analysis. Visualization modules support real-time rendering using HTML5 Canvas or external libraries, while plugins enable integration with statistical tools. AgentSimJS runs both in modern web browsers and Node.js, making it suitable for interactive web applications, academic research, educational tools, and rapid prototyping of swarm intelligence, crowd dynamics, or distributed AI experiments.

AI Receptionist is a Python and Flask-based web app integrating OpenAI’s GPT models and Google Calendar API to serve as a virtual front-desk agent. Visitors interact through a chat widget or voice interface, receiving instant answers to FAQs, custom information about services, and seamless meeting scheduling. The system logs visitor details, sends email notifications, and maintains a searchable history of interactions. It supports configuration of custom greeting scripts, automated follow-ups, and multilingual responses, making it an adaptable solution for startups, clinics, co-working spaces, and remote offices seeking modern, scalable reception automation.

ProficientAI Agent Framework is an end-to-end solution for designing and deploying advanced AI agents. It allows users to define custom agent behaviors through modular tool definitions and function specifications, ensuring seamless integration with external APIs and services. The framework’s memory management subsystem provides short-term and long-term context storage, enabling coherent multi-turn conversations. Developers can easily switch between different language models or combine them for specialized tasks. Built-in monitoring and logging tools offer insights into agent performance and usage metrics. Whether you’re building customer support bots, knowledge base search assistants, or task automation workflows, ProficientAI simplifies the entire pipeline from prototype to production, ensuring scalability and reliability.

The LLM Agents Simulation Framework enables the design, execution, and analysis of simulated environments where autonomous agents interact through large language models. Users can register multiple agent instances, assign customizable prompts and roles, and specify communication channels such as message passing or shared state. The framework orchestrates simulation cycles, collects logs, and calculates metrics like turn-taking frequency, response latency, and success rates. It supports seamless integration with OpenAI, Hugging Face, and local LLMs. Researchers can create complex scenarios—negotiation, resource allocation, or collaborative problem-solving—to observe emergent behaviors. Extensible plugin architecture allows addition of new agent behaviors, environment constraints, or visualization modules, fostering reproducible experiments.

SyntropAI is a developer-focused Python library designed to simplify the construction of autonomous AI agents. It provides a modular architecture with core components for memory management, tool and API integration, LLM backend abstraction, and a planning engine that orchestrates multi-step workflows. Users can define custom tools, configure persistent or short-term memory, and select from supported LLM providers. SyntropAI also includes logging and monitoring hooks to track agent decisions. Its plug-and-play modules let teams iterate quickly on agent behaviors, making it ideal for chatbots, knowledge assistants, task automation bots, and research prototypes.

Adorable is a low-code framework that empowers developers and businesses to build autonomous AI agents capable of performing web browsing, data extraction, API calls, and scheduled workflows. Users define objectives, triggers, and actions via a web dashboard or SDK, then test and deploy agents to the cloud or on-premise. Adorable manages authentication, error retries, and logging, while offering templates for common use cases like web scraping, email alerts, and social media monitoring. Its dashboard provides real-time insights and scalability controls, reducing development time and operational overhead for routine automation tasks.

AgentCrew is designed to streamline the creation and management of AI agents by abstracting common functionalities such as agent lifecycle, memory persistence, task scheduling, and inter-agent communication. Developers can define custom agent profiles, specify triggers and conditions, and integrate with major LLM providers like OpenAI and Anthropic. The framework provides a Python SDK, CLI tools, RESTful endpoints, and an intuitive web dashboard for monitoring agent performance. Workflow automation features allow agents to work in parallel or sequence, exchange messages, and log interactions for auditing and retraining. The modular architecture supports plugin extensions, enabling organizations to tailor the platform to diverse use cases, from customer service bots to automated research assistants and data extraction pipelines.

AI Agents for Rock Paper Scissors is an open-source Python project that demonstrates how to build, train, and evaluate different AI strategies—random play, rule-based pattern recognition, and reinforcement learning (Q-learning)—in the classic Rock-Paper-Scissors game. It provides modular agent classes, a configurable game runner, performance logging, and visualization utilities. Users can easily swap agents, adjust learning parameters, and explore AI behavior in competitive scenarios.

Blue Agent serves as a comprehensive toolkit for constructing AI-driven agents in Node.js. It enables developers to implement chain-of-thought prompting to improve reasoning, integrate external tools and APIs for enriched functionality, and maintain conversation memory for context retention. The framework features a planning engine that sequences tasks, an execution module to perform actions, and built-in logging to track agent decisions. Developers can define custom tool interfaces, orchestrate multi-step workflows, and leverage function calling to interact with services. Blue Agent's modular architecture allows seamless extension with plugins and supports debugging tools for observing agent behaviors, making it ideal for building advanced chatbots, autonomous assistants, and automated pipelines.