Learning Resources AI Agents
Compare the best open-source AI agents for learning resources. Guides, curated lists, courses and examples. Ranked by GitHub stars, with install commands, what each one can touch and scan reports where available.
Building A Coding Agent From Scratch Course
Learn harness engineering by building Claude Code from scratch. Free, open-source course: 8 articles, 6 videos, 1 codebase.
GPTSwarm
🐝 The First Self-Improving agents with RL / Prompting Optimization
Learnpython
Python Resources for Everyone
Agent Purge
One persona, many coding agents. Replace or inject system prompts across codex, claude, opencode, grok, omp, hermes, pi, zcode - with a local web console.
Most Capable Agent System Prompt
A copy-paste system prompt that has your coding agent (Claude Code, Codex, Cursor) build a self-improving agent system for any computer work.
Doc To Lora
Hypernetworks that update LLMs to remember factual information
Langgraph Course
Hands-on LangGraph course repo for building production-grade LLM agents with Agentic RAG, ReAct, and reflection workflows.
Langchain1 0 Langgraph1 0 Learning
这是一个 LangChain 1.0 和 LangGraph 1.0 的学习仓库，学习如何进行agent开发，涵盖从基础概念到实战项目的完整学习路径。
BenchMARL
BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being systematically grounded in its two core tenets: reproducibility and standardization.
Open AgentRL
RLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios
VectorizedMultiAgentSimulator
VMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set of challenging multi-robot scenarios. Additional scenarios can be implemented through a simple and modular interface.
Deerflow Book
本书围绕 DeerFlow 2.0，从理论到源码，系统讲解如何进行二次开发。(精校)
Learn Workbuddy
从 0 复刻 WorkBuddy-style 桌面 AI 助手 Harness：24 章 Python 教程，覆盖 Agent Loop、工具调用、记忆系统、Sidecar、沙盒审计、DeepSeek/OpenAI 评测轨迹
Agentic AI Systems
Practical system design, tools, and hands-on resources for building Gen-AI agents & agentic AI systems.
LoongFlow
LoongFlow is an expert-grade Agent framework for Loop Engineering. Through a Plan-Execute-Summary loop and structured experiential memory, it enables AI to continuously think, execute, reflect, and evolve across complex software engineering, mathematical, and machine learning tasks.
MineStudio
MineStudio: A Streamlined Package for Minecraft AI Agent Development
Swytchcode Examples
Swytchcode demo projects with different agents
Sotopia
Sotopia: an Open-ended Social Learning Environment (ICLR 2024 spotlight)
AI Playground
📽️ Code from tutorials presented on the "Code AI with Rok" YouTube channel
RL Matrix
Deep Reinforcement Learning in C#
Hello Agent System
👋 Hello Agent System — learn enterprise AI agent system design by building every production layer from scratch. 17 bilingual lessons (EN/中文) with tested exercises: tools, architectures, reliability, security, evals, distributed execution, cost, RAG, release ops. 企业级 Agent 系统设计训练营
Rl Rvo Nav
[RA-Letter 2022] Reinforcement Learned Distributed Multi-Robot Navigation with Reciprocal Velocity Obstacle Shaped Rewards
Learn Agent
学习Agent开发的笔记，尝试让Agent从可用到可靠
LLM Rl Environments Lil Course
🌱 A little course on Reinforcement Learning Environments for evaluating and training Language Models
List refreshed November 15, 2026. Data comes from public GitHub repositories.