# shayanthn/ai-agent-architectures architecture

> Architecture diagram of the GitHub repository shayanthn/ai-agent-architectures, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-09-26). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/shayanthn/ai-agent-architectures
- Repository: https://github.com/shayanthn/ai-agent-architectures

## Overview

This repository is an educational collection of runnable Jupyter demonstrations, not a single deployed agent service. The principal workflow is for a developer to choose and run an architecture notebook to explore its agent pattern; the notebooks cover foundational, collaborative, memory/reasoning, and safety or self-improvement designs. The README identifies LangGraph as the core orchestrator and describes LLM-as-a-Judge evaluation as a capability of most examples. Notebook internals were not sampled, so the graph does not assert specific calls between their components or identify which notebooks implement evaluation.

Main entry points: [`01_reflection.ipynb`](https://github.com/shayanthn/ai-agent-architectures/blob/main/01_reflection.ipynb) (Reflection), [`02_tool_use.ipynb`](https://github.com/shayanthn/ai-agent-architectures/blob/main/02_tool_use.ipynb) (Tool Use), [`03_ReAct.ipynb`](https://github.com/shayanthn/ai-agent-architectures/blob/main/03_ReAct.ipynb) (ReAct), [`04_planning.ipynb`](https://github.com/shayanthn/ai-agent-architectures/blob/main/04_planning.ipynb) (Planning)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_foundations["Foundational Patterns"]
  node_reflection["Reflection"]
  node_tool_use["Tool Use<br/>[02_tool_use.ipynb]"]
  node_react["ReAct<br/>[03_ReAct.ipynb]"]
  node_planning["Planning<br/>[04_planning.ipynb]"]
end

subgraph group_collaboration["Agent Collaboration"]
  node_multi_agent["Multi-Agent"]
  node_blackboard["Blackboard"]
  node_meta_controller["Meta-Controller"]
  node_ensemble["Ensemble<br/>[13_ensemble.ipynb]"]
end

subgraph group_reasoning["Memory And Reasoning"]
  node_episodic_semantic["Episodic Semantic Memory"]
  node_tree_thoughts["Tree Of Thoughts"]
  node_world_graph["World-Model Graph<br/>[12_graph.ipynb]"]
  node_cellular_automata["Cellular Automata"]
end

subgraph group_safety["Safety And Improvement"]
  node_pev["Plan Execute Verify<br/>[06_PEV.ipynb]"]
  node_mental_loop["Mental Loop"]
  node_dry_run["Dry-Run Harness<br/>[14_dry_run.ipynb]"]
  node_rlhf["RLHF<br/>[15_RLHF.ipynb]"]
  node_metacognitive["Reflexive Metacognition"]
end

node_developer(("Developer"))
node_langgraph["LangGraph"]

node_developer -->|"runs"| node_reflection
node_developer -->|"runs"| node_tool_use
node_developer -->|"runs"| node_react
node_developer -->|"runs"| node_planning
node_developer -->|"runs"| node_multi_agent
node_developer -->|"runs"| node_pev
node_developer -->|"runs"| node_blackboard
node_developer -->|"runs"| node_episodic_semantic
node_developer -->|"runs"| node_tree_thoughts
node_developer -->|"runs"| node_mental_loop
node_developer -->|"runs"| node_meta_controller
node_developer -->|"runs"| node_world_graph
node_developer -->|"runs"| node_ensemble
node_developer -->|"runs"| node_dry_run
node_developer -->|"runs"| node_rlhf
node_developer -->|"runs"| node_cellular_automata
node_developer -->|"runs"| node_metacognitive
node_reflection -->|"orchestrates with"| node_langgraph
node_tool_use -->|"orchestrates with"| node_langgraph
node_react -->|"orchestrates with"| node_langgraph
node_planning -->|"orchestrates with"| node_langgraph
node_multi_agent -->|"orchestrates with"| node_langgraph
node_pev -->|"orchestrates with"| node_langgraph
node_blackboard -->|"orchestrates with"| node_langgraph
node_episodic_semantic -->|"orchestrates with"| node_langgraph
node_tree_thoughts -->|"orchestrates with"| node_langgraph
node_mental_loop -->|"orchestrates with"| node_langgraph
node_meta_controller -->|"orchestrates with"| node_langgraph
node_world_graph -->|"orchestrates with"| node_langgraph
node_ensemble -->|"orchestrates with"| node_langgraph
node_dry_run -->|"orchestrates with"| node_langgraph
node_rlhf -->|"orchestrates with"| node_langgraph
node_cellular_automata -->|"orchestrates with"| node_langgraph
node_metacognitive -->|"orchestrates with"| node_langgraph

click node_reflection "https://github.com/shayanthn/ai-agent-architectures/blob/main/01_reflection.ipynb"
click node_tool_use "https://github.com/shayanthn/ai-agent-architectures/blob/main/02_tool_use.ipynb"
click node_react "https://github.com/shayanthn/ai-agent-architectures/blob/main/03_ReAct.ipynb"
click node_planning "https://github.com/shayanthn/ai-agent-architectures/blob/main/04_planning.ipynb"
click node_multi_agent "https://github.com/shayanthn/ai-agent-architectures/blob/main/05_multi_agent.ipynb"
click node_pev "https://github.com/shayanthn/ai-agent-architectures/blob/main/06_PEV.ipynb"
click node_blackboard "https://github.com/shayanthn/ai-agent-architectures/blob/main/07_blackboard.ipynb"
click node_episodic_semantic "https://github.com/shayanthn/ai-agent-architectures/blob/main/08_episodic_with_semantic.ipynb"
click node_tree_thoughts "https://github.com/shayanthn/ai-agent-architectures/blob/main/09_tree_of_thoughts.ipynb"
click node_mental_loop "https://github.com/shayanthn/ai-agent-architectures/blob/main/10_mental_loop.ipynb"
click node_meta_controller "https://github.com/shayanthn/ai-agent-architectures/blob/main/11_meta_controller.ipynb"
click node_world_graph "https://github.com/shayanthn/ai-agent-architectures/blob/main/12_graph.ipynb"
click node_ensemble "https://github.com/shayanthn/ai-agent-architectures/blob/main/13_ensemble.ipynb"
click node_dry_run "https://github.com/shayanthn/ai-agent-architectures/blob/main/14_dry_run.ipynb"
click node_rlhf "https://github.com/shayanthn/ai-agent-architectures/blob/main/15_RLHF.ipynb"
click node_cellular_automata "https://github.com/shayanthn/ai-agent-architectures/blob/main/16_cellular_automata.ipynb"
click node_metacognitive "https://github.com/shayanthn/ai-agent-architectures/blob/main/17_reflexive_metacognitive.ipynb"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_reflection,node_tool_use,node_react,node_planning toneBlue
class node_multi_agent,node_blackboard,node_meta_controller,node_ensemble toneAmber
class node_episodic_semantic,node_tree_thoughts,node_world_graph,node_cellular_automata toneMint
class node_pev,node_mental_loop,node_dry_run,node_rlhf,node_metacognitive toneRose
class node_developer,node_langgraph toneIndigo
```

## Components

### Foundational Patterns

- [Reflection](https://github.com/shayanthn/ai-agent-architectures/blob/main/01_reflection.ipynb): `01_reflection.ipynb`
- [Tool Use](https://github.com/shayanthn/ai-agent-architectures/blob/main/02_tool_use.ipynb): `02_tool_use.ipynb`
- [ReAct](https://github.com/shayanthn/ai-agent-architectures/blob/main/03_ReAct.ipynb): `03_ReAct.ipynb`
- [Planning](https://github.com/shayanthn/ai-agent-architectures/blob/main/04_planning.ipynb): `04_planning.ipynb`

### Agent Collaboration

- [Multi-Agent](https://github.com/shayanthn/ai-agent-architectures/blob/main/05_multi_agent.ipynb): `05_multi_agent.ipynb`
- [Blackboard](https://github.com/shayanthn/ai-agent-architectures/blob/main/07_blackboard.ipynb): `07_blackboard.ipynb`
- [Meta-Controller](https://github.com/shayanthn/ai-agent-architectures/blob/main/11_meta_controller.ipynb): `11_meta_controller.ipynb`
- [Ensemble](https://github.com/shayanthn/ai-agent-architectures/blob/main/13_ensemble.ipynb): `13_ensemble.ipynb`

### Memory And Reasoning

- [Episodic Semantic Memory](https://github.com/shayanthn/ai-agent-architectures/blob/main/08_episodic_with_semantic.ipynb): `08_episodic_with_semantic.ipynb`
- [Tree Of Thoughts](https://github.com/shayanthn/ai-agent-architectures/blob/main/09_tree_of_thoughts.ipynb): `09_tree_of_thoughts.ipynb`
- [World-Model Graph](https://github.com/shayanthn/ai-agent-architectures/blob/main/12_graph.ipynb): `12_graph.ipynb`
- [Cellular Automata](https://github.com/shayanthn/ai-agent-architectures/blob/main/16_cellular_automata.ipynb): `16_cellular_automata.ipynb`

### Safety And Improvement

- [Plan Execute Verify](https://github.com/shayanthn/ai-agent-architectures/blob/main/06_PEV.ipynb): `06_PEV.ipynb`
- [Mental Loop](https://github.com/shayanthn/ai-agent-architectures/blob/main/10_mental_loop.ipynb): `10_mental_loop.ipynb`
- [Dry-Run Harness](https://github.com/shayanthn/ai-agent-architectures/blob/main/14_dry_run.ipynb): `14_dry_run.ipynb`
- [RLHF](https://github.com/shayanthn/ai-agent-architectures/blob/main/15_RLHF.ipynb): `15_RLHF.ipynb`
- [Reflexive Metacognition](https://github.com/shayanthn/ai-agent-architectures/blob/main/17_reflexive_metacognitive.ipynb): `17_reflexive_metacognitive.ipynb`

### Other components

- **Developer**
- **LangGraph**

## Connections

- Developer → Reflection: runs
- Developer → Tool Use: runs
- Developer → ReAct: runs
- Developer → Planning: runs
- Developer → Multi-Agent: runs
- Developer → Plan Execute Verify: runs
- Developer → Blackboard: runs
- Developer → Episodic Semantic Memory: runs
- Developer → Tree Of Thoughts: runs
- Developer → Mental Loop: runs
- Developer → Meta-Controller: runs
- Developer → World-Model Graph: runs
- Developer → Ensemble: runs
- Developer → Dry-Run Harness: runs
- Developer → RLHF: runs
- Developer → Cellular Automata: runs
- Developer → Reflexive Metacognition: runs
- Reflection → LangGraph: orchestrates with
- Tool Use → LangGraph: orchestrates with
- ReAct → LangGraph: orchestrates with
- Planning → LangGraph: orchestrates with
- Multi-Agent → LangGraph: orchestrates with
- Plan Execute Verify → LangGraph: orchestrates with
- Blackboard → LangGraph: orchestrates with
- Episodic Semantic Memory → LangGraph: orchestrates with
- Tree Of Thoughts → LangGraph: orchestrates with
- Mental Loop → LangGraph: orchestrates with
- Meta-Controller → LangGraph: orchestrates with
- World-Model Graph → LangGraph: orchestrates with
- Ensemble → LangGraph: orchestrates with
- Dry-Run Harness → LangGraph: orchestrates with
- RLHF → LangGraph: orchestrates with
- Cellular Automata → LangGraph: orchestrates with
- Reflexive Metacognition → LangGraph: orchestrates with