# evoiz/agentic-design-patterns

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/evoiz-agentic-design-patterns).**

_How this analysis was created: the description and tags below were written by an AI model that read this project's README and public documentation pages; stars, license and language come straight from the GitHub API. The model does not read the source code._

4,064 stars · 633 forks · Jupyter Notebook

## Links

- GitHub: https://github.com/evoiz/Agentic-Design-Patterns
- awesome-repositories: https://awesome-repositories.com/repository/evoiz-agentic-design-patterns.md

## Description

Agentic Design Patterns is a book-length handbook on designing and building LLM-powered agent systems, delivered as a collection of Jupyter notebooks. It spans twenty-one chapters and seven appendices, organized from foundational patterns through advanced, production, and enterprise topics, and each chapter has a matching notebook with runnable code that readers execute and modify cell by cell.

The patterns covered include prompt chaining, runtime request routing, tool use through standard interfaces, persistent memory with learning and goal tracking, and retrieval-augmented generation. Multi-agent coordination is treated as its own topic, with cooperating agents that divide work and exchange messages directly. A production-focused thread covers guardrails, human oversight, exception handling and recovery, and evaluation for building robust and safe agent deployments.

The material is organized into skill-based learning tracks, so it can be used for self-paced study or as lecture and lab material for instructors. Researchers can also use the reference implementations to compare approaches and extend patterns to new use cases. Contributions such as bug reports, pattern suggestions, documentation updates, code improvements, and translations are accepted through a fork, branch, and pull request workflow.

## Tags

### Artificial Intelligence & ML

- [Autonomous Agent Patterns](https://awesome-repositories.com/f/artificial-intelligence-ml/autonomous-agent-patterns.md) — Teaches how to design and build LLM agent systems through a full book of patterns spanning twenty-one chapters and seven appendices. ([source](https://github.com/evoiz/agentic-design-patterns#readme))
- [Multi-Agent Coordination Systems](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/orchestration-engines/ai-agent/multi-agent-coordination-systems.md) — Covers cooperating agents that communicate directly and divide work to solve problems together. ([source](https://github.com/evoiz/agentic-design-patterns#readme))
- [Message-Passing Agent Orchestrators](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/orchestration-engines/ai-agent/multi-agent-coordination-systems/message-passing-agent-orchestrators.md) — Shows cooperating agents that divide work and exchange messages directly to solve problems collaboratively.
- [Agent Memory Management](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-memory-management.md) — Covers memory management, learning techniques, and goal tracking so agents persist state across interactions and adapt over time. ([source](https://github.com/evoiz/agentic-design-patterns#readme))
- [Agent Memory Persistence](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-memory-persistence.md) — Covers persistent memory, learning and goal tracking so agents adapt their behavior based on earlier interactions.
- [Agent Reliability Engineering](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-reliability-engineering.md) — Covers guardrails, human oversight, error recovery, evaluation and grounded retrieval for making agent systems robust and safe in deployment.
- [Human-in-the-Loop Oversight](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agentic-workflows/human-in-the-loop-oversight.md) — Covers human review points and oversight of agent actions, alongside guardrails and error recovery, for building controllable agent deployments.
- [Agent Tool Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/agent-frameworks/tool-use-and-execution/agent-tool-integrations.md) — Connects agents to external tools and standard interfaces so they can take actions beyond text generation. ([source](https://github.com/evoiz/agentic-design-patterns#readme))
- [Retrieval-Augmented Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/conversational-interfaces/retrieval-augmented-generation.md) — Explains fetching relevant external documents and adding them to the prompt to ground model answers in information it was not trained on.
- [Prompt Chaining](https://awesome-repositories.com/f/artificial-intelligence-ml/language-model-orchestration/ai-workflow-patterns/prompt-chaining.md) — Teaches splitting a complex task into ordered prompt steps where each output feeds the next to build the final result.
- [Multi-Agent Systems](https://awesome-repositories.com/f/artificial-intelligence-ml/language-model-orchestration/multi-agent-systems.md) — Shows cooperating agents that divide work and exchange messages to solve complex problems collaboratively.
- [Production Readiness Practices](https://awesome-repositories.com/f/artificial-intelligence-ml/production-readiness-practices.md) — Covers exception handling and recovery, human oversight, guardrails, retrieval grounding and evaluation for building robust and safe agent deployments. ([source](https://github.com/evoiz/agentic-design-patterns#readme))
- [Task Decompositions](https://awesome-repositories.com/f/artificial-intelligence-ml/task-decompositions.md) — Teaches breaking complex tasks into ordered prompt steps and routing requests to suitable handlers so outputs feed one another.
- [Tool-Calling Agent Loops](https://awesome-repositories.com/f/artificial-intelligence-ml/tool-calling-agent-loops.md) — Shows an agent loop that repeatedly decides whether to call external tools through standard interfaces to act beyond text generation.

### Education & Learning Resources

- [Design Pattern Books](https://awesome-repositories.com/f/education-learning-resources/programming-books/design-pattern-books.md) — Delivers a book-length handbook on designing LLM-powered agent systems through foundational, advanced, production and enterprise patterns across chapters and appendices.
- [AI Agent Architecture Study Guides](https://awesome-repositories.com/f/education-learning-resources/ai-agent-architecture-study-guides.md) — Explains how to structure LLM agents using prompt chaining, routing, tool use, memory, retrieval-augmented generation and goal tracking. ([source](https://github.com/evoiz/agentic-design-patterns#readme))
- [AI Agent Design Pattern Courses](https://awesome-repositories.com/f/education-learning-resources/ai-agent-design-pattern-courses.md) — Teaches how to design and build AI agent systems through a structured book and runnable chapter notebooks from foundations to enterprise.
- [Chapter Sample Code](https://awesome-repositories.com/f/education-learning-resources/chapter-sample-code.md) — Provides a notebook per chapter with practical examples that readers run cell by cell to learn each agent pattern by doing. ([source](https://github.com/evoiz/agentic-design-patterns#readme))
- [Jupyter Notebook Curricula](https://awesome-repositories.com/f/education-learning-resources/jupyter-notebook-curricula.md) — Ships a per-chapter set of Jupyter notebooks with runnable code that readers execute and modify cell by cell.
- [Embedded Notebook Executions](https://awesome-repositories.com/f/education-learning-resources/jupyter-notebook-curricula/embedded-notebook-executions.md) — Delivers each chapter as a runnable Jupyter notebook where explanatory text and code sit together and can be executed and modified cell by cell.

### Data & Databases

- [Agent State Persistence](https://awesome-repositories.com/f/data-databases/agent-state-persistence.md) — Teaches storing agent state and learned context between interactions so later behavior adapts to earlier events.

### Web Development

- [Request Routing](https://awesome-repositories.com/f/web-development/request-routing.md) — Demonstrates inspecting incoming requests at runtime and directing each to the most suitable handler along different processing paths.