Discover great AI tools
📢 NoticeWebsite launched:DeepToSeek AI tools directory is live. Submit great tools and get featured!
Home / Open Source Radar / Learning / AgentGuide

An AI agent engineering guide covering agent harness design, context engineering, advanced RAG, MCP, agentic RL and LangGraph, plus a large LLM interview question bank.

Stars12.1k
Forks1.1k
LanguageMDX
LicenseCC-BY-4.0
Last push2026-11-05

About this project

AgentGuide is an open-source learning resource project on GitHub: An AI agent engineering guide covering agent harness design, context engineering, advanced RAG, MCP, agentic RL and LangGraph, plus a large LLM interview question bank. It is a learning resource rather than a running service: courses, curated lists, tutorials or reference implementations that explain how the field actually works. It is maintained by adongwanai and published as a public repository you can read, fork and run yourself.

On GitHub the repository is tagged agentic-rl, agenticrag, ai-agent, claude-code, crewai, graphrag, grpo, harness, interview and job-hunting, which is a fair summary of what it covers. The value is in the structure and the worked examples, so check how recently it was updated before following it end to end.

It is written mainly in MDX and released under CC-BY-4.0, a documentation-style license — check that its terms fit software before shipping it. It is actively maintained: the most recent commit landed on November 5, 2026.

To try it, clone the repository and follow its README; that file is the canonical install guide. There is also a project page at https://adongwanai.github.io/AgentGuide/ for documentation or a hosted demo. Because it runs on your own infrastructure, budget time for environment setup: dependencies, model weights and configuration usually take longer than the first successful run.

Key facts as recorded on GitHub: 12,065 stars; 1,142 forks; primary language MDX; license CC-BY-4.0; last commit on November 5, 2026; topics agentic-rl, agenticrag, ai-agent, claude-code, crewai, graphrag.