MARFT is a Python-based LLMs, enabling reproducible experiments and rapid prototyping of collaborative AI systems.

Self-Determining AI Agents is a Python-based framework designed to simplify the creation of autonomous AI agents. It features a customizable planning loop where agents generate tasks, plan strategies, and execute actions using integrated tools. The framework includes persistent memory modules for context retention, a flexible task scheduling system, and hooks for custom tool integrations such as web APIs or database queries. Developers define agent goals via configuration files or code, and the library handles the iterative decision-making process. It supports logging, performance monitoring, and can be extended with new planning algorithms. Ideal for research, automating workflows, and prototyping intelligent multi-agent systems.

Agenite is a Python-centric AI agent framework designed to streamline the creation, orchestration, and management of autonomous agents. It offers modular components such as memory stores, task schedulers, and event-driven communication channels, enabling developers to build agents capable of stateful interactions, multi-step reasoning, and asynchronous workflows. The platform provides adapters for connecting to external APIs, databases, and message queues, while its pluggable architecture supports custom modules for natural language processing, data retrieval, and decision-making. With built-in storage backends for Redis, SQL, and in-memory caches, Agenite ensures persistent agent state and enables scalable deployments. It also includes a command-line interface and JSON-RPC server for remote control, facilitating integration into CI/CD pipelines and real-time monitoring dashboards.

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.