AI tools, scored for your job
Get paid to train AI
🤝 You're in the Free & Open Source library — community-built tools you can use without paying. A different concept from our scored AI directory.
Home › Free & Open Source › Writing › GenAI_Agents
✦ Free & open sourceWriting

GenAI_Agents

Over 64 Jupyter notebooks and tutorials for building GenAI agents from scratch.

GenAI Agents Code and Tutorials

Master AI agent development with practical Jupyter notebooks and implementation patterns.

Free forever · source-available · Licence not stated in the repository
✓ Light setup✓ Browser-based✓ Real-time collaboration
8.4
ZEKAI
Essential agent code resource
Free & open source · Writing
Ease of setup7
Usefulness8
Maintenance9.5
Community9.2
★ 24,938
GITHUB
Nov 2026
UPDATED
Licence not stated in the repository
LICENSE
🛠 Don't want to self-host? We can set it up →
⚡ Quick answer

This repository provides over 64 tutorials and implementations for Generative AI agents, spanning basic conversational bots to complex multi-agent setups. It suits developers and AI practitioners wanting code-first examples using LangChain and LangGraph.

Runs on
Cross-platform
Hosting
Desktop
Languages
Jupyter Notebook
License
Licence not stated in the repository

What it is

It delivers practical Python implementations of core agent patterns like thinking budgets, reflection, and plan-then-execute loops. The notebooks are updated for modern LangChain and LangGraph 1.x environments with current model IDs.

Who it's for

It suits developers and engineers wanting to understand the code behind AI agents. It does not suit non-technical users looking for a pre-built application or a no-code platform.

Key features

64+ Tutorials

Explore growing collections of agent implementations and patterns.

Core Agent Patterns

Build reflection, planning, and tool-use mechanics from scratch.

Updated for LangGraph

Access code configured to import cleanly on modern LangChain and LangGraph 1.x.

Related Repositories

Jump directly to companion projects for RAG, memory, and prompt engineering.

How to start

Up and running in 3 steps

1
Clone the GenAI_Agents repository from GitHub to your local environment.
2
Open the Jupyter notebooks to explore individual agent tutorials and patterns.
3
Configure your required model API keys to run the implementations.
Real talk

Our honest verdict

What's great

  • Provides practical code for complex agent patterns like reflection and planning.
  • Companion to the bestselling book AI Agents Made Simple.
  • Includes links to specialized sub-repositories for memory and prompt engineering.
  • Actively maintained with updated model IDs and framework imports.

Where it falls short

  • Requires you to bring your own API keys for underlying language models.
  • Not every notebook has been run end to end against live services.
  • Requires working knowledge of Python and Jupyter notebooks to utilize.
Cost

Pricing & license

The repository is free to use, though running the notebooks requires API calls to commercial LLM providers which incur usage costs.

Paid work

Open remote AI-training roles

880 open remote AI-training roles, updated November 15, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.

See all open roles →
Compare

Alternatives

🎁 Free & open-source alternatives
Get more

Use it, or have us set it up

📄 Free PDF: GenAI_Agents for Writing
A plain-language guide to getting your first result. Sent to your inbox.
🔔 64 people want a full video tutorial — add your vote
🛠 Don't want to set it up yourself?
We'll install, host & configure GenAI_Agents for you — and train your team.
Get it done for you ↗
Questions

FAQ

What frameworks do these tutorials use?

The notebooks primarily use Python along with LangChain and LangGraph frameworks.

Are API keys included?

No, each notebook requires you to supply your own provider API keys.

Radar

Latest AI news

✉️ The weekly free toolkit
The best new free & open-source tools for Writing — one short email a week, in your language.
Free · 1 email/week · unsubscribe anytime
Get paid to train AI →

See Zekai first in Google