Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Learn AI agents from scratch.
| Date | Stars |
|---|---|
| 2026-07-31 | 445 |
| 2026-08-06 | 445 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
60.0
growth rate 0.00%/day
<h1 align="center" style="margin-top: 0;">Awesome Agent Architecture</h1> <p align="center"> <strong>Learn how modern AI agents are built around the LLM.</strong><br> </p> <p align="center"> <a href="#sections"><img src="https://img.shields.io/badge/Focus-Harness_Engineering-8250df" alt="Focus: Harness Engineering"></a> <a href="#systems-under-study"><img src="https://img.shields.io/badge/Systems-3+-0969da" alt="Systems"></a> <a href="#sections"><img src="https://img.shields.io/badge/Sections-22-2da44e" alt="Sections"></a> <a href="LICENSE"><img src="https://img.shields.io/badge/License-MIT-d29922" alt="License"></a> </p> <p align="center"> <img src="https://github.com/user-attachments/assets/472d8152-5e46-4e39-9f09-e77dcd07936a" alt="Awesome Agent Architecture"> </p> <p align="center"> <strong>English</strong> · <a href="README.zh-TW.md">繁體中文</a> · <a href="README.zh-CN.md">简体中文</a> </p> The model reasons. The harness gives it action, state, and limits: it runs tools, keeps state across calls, gates side effects, and coordinates loops, none of which a model call does by itself. This repo explains the harness section by section: loop, tools, memory, permissions, context, tasks, and interfaces. Learn it once and you can read many agents, since a coding tool, chat assistant, and autonomous runner mostly differ in harness choices. **Contents:** [Loop](#the-agent-loop) · [Method](#how-to-learn) · [Systems](#systems-under-study) · [Sections](#sections) · [Structure](#repository-structure) · [Running](#running-the-demos) --- ## The Agent Loop  Most agents share the same control flow: call the model, run requested tools, append results, and call the model again. The loop is small. Most engineering is around it: dispatch tools, gate side effects, manage context, persist state, and coordinate other loops. --- ## How to learn Every section is self-contained and uses the same four-part lens: 1. **Opening.** What problem this layer solves. 2. **Mechanism.** The general design and control flow. 3. **Per system.** How real systems implement it. 4. **Failure modes.** What breaks and how to mitigate it. To learn from this repo: - **Read the sections in order. Each builds on the layer before it**. - For a runnable section, read `src/loop.py`, then run its `demo.py`. - Diff a section's `src/` against the section before it. The diff is the one mechanism that section adds. --- ## Systems Under Study Each system is a worked example for the sections below. | System | Why people use it | Read it for | Sections | Version studied | | ---------------------- | ------------------------------------------------------------------------------- | ---------------------------------- | -------------------- | --------------- | | **Claude Code** | Frontier coding agent: edits files, runs commands, ships changes in real repos. | The full harness, start here | 0 to 21 (all) | v2.1.88 | | **Hermes Agent** | Long-term assistant: remembers you, learns workflows, runs anywhere. | Memory, skills, always-on channels | 7, 9, 14, 16, 19, 21 | v2026.7.1 | | **mini-swe-agent** | Research baseline: one bash tool, about 150 lines. | The smallest complete loop, budgets, eval harness | 0 to 3, 8, 10, 11, 20, 21 | v2.4.5 | | *(more soon)* | | | | | > More systems can be added later, including OpenClaw and aider. > The memory layer also has a companion repo: [learn-agent-memory](https://github.com/hardness1020/learn-agent-memory). --- ## Sections Eight layers, from the basic loop to a harness that runs itself. Each row links to one self-contained writeup. > Section 9 continues in [learn-agent-
Excerpt of 13,482 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:b00faa50cc44e136, topic:ai-agents, topic:agentic-ai, desc:ai agents