A 27-chapter hands-on tutorial for building an autonomous AI agent from zero in Python. Agent loop, tool system, memory, skills, MCP, multi-platform gateway, and self-evolution — inspired by Hermes Agent.
从零构建 AI Agent——每一步都有源码，每一章都能运行，渐进式理解智能体。Build an AI Agent from Scratch — Learn AI Agents step by step with runnable source code.
纯 Python 手写的极简 coding agent — 对照 Claude Code + Hermes 真源码复刻 agent 内核（工具系统/权限门/子 agent 并行/skill 渐进披露/联网），无 LangChain。
A complete AI agent in ~200 lines of Python. No frameworks. Learn how LLM agents actually work.
An autonomous AI research assistant built from scratch using the ReAct (Reasoning + Acting) paradigm. Features a cost-aware multi-LLM routing engine (Gemini 3.1 Flash Lite + Groq LLaMA 3.3 70B) grounded with real-time web execution via the Tavily Search API. Generates downloadable markdown analysis reports and reasoning traces.
Add a description, image, and links to the agent-from-scratch topic page so that developers can more easily learn about it.
To associate your repository with the agent-from-scratch topic, visit your repo's landing page and select "manage topics."