neural-maze/agentic-patterns-course resource

Health v2 · maintenance only

Adoption not part of the score

1743 stars · 336 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Jupyter Notebook course implementing the four agentic patterns (reflection, tool use, planning/ReAct, and multiagent) from scratch using raw Groq API calls, with no frameworks like LangChain or CrewAI. It includes step-by-step notebooks and complete Python implementations for each pattern.

Use cases

• learn how to build AI agents from scratch without frameworks
• implement the reflection pattern for LLM self-improvement
• build a ReAct agent with tool use using raw API calls
• understand Andrew Ng's four agentic patterns
• create a multiagent crew with plain Groq API calls
• study agent design patterns with worked notebooks

When to choose

• you want to understand agent internals rather than use LangChain or CrewAI abstractions
• you prefer learning via step-by-step Jupyter notebooks
• you want framework-free implementations using the Groq API

When to avoid

• you need a production-ready agent framework with built-in features
• you use a different LLM provider and don't want to adapt the Groq-specific code
• you need maintained, versioned software rather than educational material

Facets

learning-resource · maturity active

agent-framework llm-inference prompt-engineering artificial-intelligence large-language-models tutorials python agentic-patterns groq jupyter-notebooks reflection-pattern tool-use planning-pattern multiagent from-scratch educational ai-agents

Member repositories

For agents

markdown · JSON · MCP: product_card(name="neural-maze/agentic-patterns-course")