Agent-Go provides a modular framework for building autonomous AI agents in Go. It integrates LLM providers (such as OpenAI), vector-based memory stores for long-term context retention, and a flexible planning engine that breaks down user requests into executable steps. Developers define and register custom tools (APIs, databases, or shell commands) that agents can invoke. A conversation manager tracks dialog history, while a configurable planner orchestrates tool calls and LLM interactions. This allows teams to rapidly prototype AI-driven assistants, automated workflows, and task-oriented bots in a production-ready Go environment.

Fast-LLM-Agent-MCP is a lightweight, open-source Python framework for building AI agents that combine memory management, chain-of-thought reasoning, and multi-step planning. Developers can integrate it with OpenAI, Azure OpenAI, local Llama, and other models to maintain conversational context, generate structured reasoning traces, and decompose complex tasks into executable subtasks. Its modular design allows custom tool integration and memory stores, making it ideal for applications like virtual assistants, decision support systems, and automated customer support bots.