Tiny-OAI-MCP-Agent provides a small, extensible agent architecture built on the OpenAI API. It implements a multi-cognitive process (MCP) loop for reasoning, memory, and tool usage. You define tools (APIs, file operations, code execution), and the agent plans tasks, recalls context, invokes tools, and iterates on results. This minimal codebase allows developers to experiment with autonomous workflows, custom heuristics, and advanced prompt patterns while handling API calls, state management, and error recovery automatically.

AI Agent with MCP is a comprehensive framework designed to streamline the development of advanced AI agents capable of maintaining long-term context, performing multi-step reasoning, and adapting strategies based on memory. It leverages a modular design comprising Memory Manager, Conditional Planner, and Prompt Manager, allowing custom integrations and extension with various LLMs. The Memory Manager persistently stores past interactions, ensuring context retention. The Conditional Planner evaluates conditions at each step and dynamically selects the next action. The Prompt Manager formats inputs and chains tasks seamlessly. Built in Python, it integrates with OpenAI GPT models via API, supports retrieval-augmented generation, and facilitates conversational agents, task automation, or decision support systems. Extensive documentation and examples guide users through setup and customization.

AL3RT Personalized harnesses advanced AI technology to provide users with highly personalized alerts and task management. It operates in real-time, adapting to your context and preferences to help streamline your responsibilities and notifications. This intuitive assistant learns from your patterns, ensuring that the information delivered is relevant and timely, enabling you to stay organized and efficient in your daily tasks.

Dial4JaCa is a Java library plugin for the JaCaMo multi-agent platform that intercepts inter-agent messages, encodes agent intentions, and routes them through LLM backends (OpenAI, local models). It manages dialogue context, updates belief bases, and integrates response generation directly into AgentSpeak(L) reasoning cycles. Developers can customize prompts, define dialogue artifacts, and handle asynchronous calls, enabling agents to interpret user utterances, coordinate tasks, and retrieve external information in natural language. Its modular design supports error handling, logging, and multi-LLM selection, ideal for research, education, and rapid prototyping of conversational MAS.

MInD is a Python-based memory framework designed to augment LLM-driven AI agents with robust memory capabilities. It enables agents to capture user inputs and system events as episodic logs, condense those logs into semantic summaries, and retrieve contextually relevant memories on demand. With configurable retention policies, similarity search, and automated summarization, MInD maintains a persistent knowledge base that agents consult during inference. This ensures they recall prior interactions accurately, adapt responses based on history, and deliver personalized, coherent dialogues across multiple sessions.