Theme
AI Resources
AI Cookbook
Dave Ebbelaar’s AI Cookbook collects Python examples and tutorials for people building AI systems. Its folders cover agent building blocks, web context, knowledge, MCP, models, and workflow patterns.
Start with a topic you need, read its explanation and code together, then adapt an example to your own project. This is a learning and reference repository, not a finished AI app or a single installable framework. Use this as a first read, not a recommendation. Open the original project before trusting details like terms, limits, privacy, cost, setup, or safety.
What it is
Examples you can inspect
The public repository groups tutorials and code by topic. It includes small agent components, web-search context examples, MCP material, model examples, and workflow patterns.
Why it stands out
Build from the pieces
The agent building-blocks section pairs explanations with separate Python files for model calls, memory, tools, validation, control, recovery, and human feedback. You can inspect one piece before combining it with others.
Availability
Public GitHub repository
You can browse the tutorials and source code on GitHub. The repository declares an MIT license; individual examples may need Python packages, provider credentials, or other setup described in their own folders.
Why it matters
What makes it useful
A tutorial is more useful when you can see where a model call sits among ordinary application steps. The cookbook gives builders code to read and change, so they can decide which parts of an AI workflow they actually need.
What to know
Where it fits
Use it as a starting point for learning or prototyping a specific AI-system component. The examples are not a packaged production platform, and their dependencies and external services differ by folder.
Notable points
What stands out
The agent building-blocks folder is a clear first stop: read its overview, then open the individual Python examples for tools, validation, recovery, or feedback. Other folders let you follow a narrower topic such as web context or MCP.
Before using
What to review
Check the example’s nearby README and dependency file, where provided; setup differs by section.
Check which provider keys, API calls, or external services an example uses before running it with your data.
Review and adapt the code, dependencies, error handling, and access permissions for your own project rather than treating a tutorial as a deployed system.
Reader fit
Who may find it relevant
Python developers looking for a concrete starting point for agents, web context, MCP, or model workflows.
Learners who want to read both an explanation and the code behind a small AI-system component.
Less relevant if you need a ready-to-use chatbot or a maintained application with one-click setup.
Editorial note
Why LifeHubber lists it
AI Cookbook makes the moving parts of an AI system visible in small, inspectable examples. That helps a builder choose a component to learn or adapt without committing to a whole framework or mistaking tutorial code for a finished app.
Source links
Source materials
Reader note
Before relying on this entry
LifeHubber lists entries to help readers inspect AI projects, not to endorse them or prove they are safe, suitable, accurate, maintained, or right for a specific use. We do not verify every entry in depth. Before relying on anything listed, review the original materials, terms, privacy practices, limits, and risks that matter for your situation.
More in AI Agents
Keep browsing this category
Explore more AI agent projects.
RAGFlow
infiniflow/ragflow
A self-hostable RAG and agent-context platform whose v0.27 line adds Knowledge Compilation, Agentic RAG thinking modes, document and data-source connectors, citations, APIs, and agent workflows.
Open Notebook
lfnovo/open-notebook
A self-hosted AI research workspace for organizing sources, chatting with selected material, searching with full-text or vector retrieval, writing notes, generating multi-speaker podcasts, and choosing local or cloud model providers.
Koog
JetBrains/koog
A JetBrains Kotlin and Java framework for building AI agents with tools, graph workflows, memory, RAG, MCP, A2A, Agent Client Protocol, tracing, Spring Boot, Ktor, and multiple LLM providers.
For project maintainers
Listed here? You can use the badge.
If you maintain a project with a current LifeHubber listing, you may add the optional “Listed on LifeHubber AI Resources” badge to its README, docs, or website. No introduction or permission request is needed.
