從零開始建構AI代理程式：使用本地LLM逐步實現

Navigation Menu

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

To see all available qualifiers, see our documentation.

Build AI agents from first principles using a local LLM - no frameworks, no cloud APIs, no hidden reasoning.

License

Uh oh!

There was an error while loading. Please reload this page.

pguso/agents-from-scratch

Folders and files

Latest commit

History

Repository files navigation

AI Agents from Scratch

A gentle, local-first introduction to AI agents.

This repository teaches how AI agents actually work by building one agent step by step from a single local LLM call.

No frameworks. No cloud APIs. No hidden reasoning. No magic.

Philosophy

Agents are not personalities. They are loops, state, and constraints.

If something feels like magic, open the file — there is no hidden logic in this repo.

What You Will Learn

This repository builds one continuously evolving agent across 10 lessons:

Who This Is For

This repo is for:

This repo is NOT for:

Quick Start

For detailed setup instructions, see QUICKSTART.md

In short:

Note: The complete_example.py file contains executable code examples demonstrating all 10 lessons. You can use it as a reference to see how all the concepts fit together.

Repository Structure

Key Files Explained

agent/agent.py - The heart of the repository

complete_example.py - Learning reference

Relationship:

What This Repo Is Not

Core Principles

Learning Path

Each lesson builds on the previous one. Do not skip ahead.

The curriculum is designed to build understanding gradually:

Contributing

This is an educational repository. Contributions should:

License

MIT License - see LICENSE file

Acknowledgments

This repository synthesizes best practices from modern agent development while deliberately avoiding complexity that obscures understanding.

If you find this useful, please star the repository and share it with others learning about AI agents.

About

Build AI agents from first principles using a local LLM - no frameworks, no cloud APIs, no hidden reasoning.

Topics

Resources

License

Contributing

Uh oh!

There was an error while loading. Please reload this page.

Stars

Watchers

Forks

Languages

Footer

Footer navigation