https://blog.0xnullpath.cc/en/tags/ai-agent/Recent content in AI Agent on Code NowHugoenTue, 27 May 2025 16:04:10 +0000https://blog.0xnullpath.cc/en/posts/note-snippet-9-llm-life-from-scratch-how-to-write-an-agent/Tue, 27 May 2025 16:04:10 +0000https://blog.0xnullpath.cc/en/posts/note-snippet-9-llm-life-from-scratch-how-to-write-an-agent/<blockquote> <p>This article aims to explain what an LLM Agent is in plain language and to implement a simple Agent in Python.</p> </blockquote><h2 id="1-introduction-to-agents">1. Introduction to Agents</h2> <h3 id="11-what-is-an-agent">1.1 What Is an Agent?</h3> <p>There is no precise definition of an LLM Agent, but one core characteristic stands out:</p> <blockquote> <p>An LLM serves as the main controller or &ldquo;brain&rdquo; that controls a flow of operations needed to complete a task or user request. &mdash;《Prompt Engineering Guide》</p>https://blog.0xnullpath.cc/en/posts/note-snippet-5-llm-agent-programming-from-scratch-the-mcp-edition/Mon, 21 Apr 2025 08:23:57 +0000https://blog.0xnullpath.cc/en/posts/note-snippet-5-llm-agent-programming-from-scratch-the-mcp-edition/<h2 id="1-what-is-mcp-model-context-protocol">1. What Is MCP (Model Context Protocol)</h2> <p>MCP (Model Context Protocol) is a communication protocol launched and open-sourced by Anthropic in 2024, designed to solve the connection problem between large language models (LLMs) and external data sources and tools. It defines the protocol for communication between the Model and external interfaces/data/Prompts. Tool/resource providers only need to implement the MCP protocol to connect with an LLM APP that implements an MCP client. During runtime, the LLM APP automatically retrieves the tool list/Prompt/resource list returned by the protocol from the MCP server via JsonRpc.</p>