Runnable Blueprints & Scaffolds

Root code-examples/

Production Code Scaffolds

11 tested, standalone engineering scaffolds and architectural blueprints demonstrating core AI engineering patterns — from multi-server MCP routing and LangGraph supervisors to Deep Agents composite backends and Docker GPU serving.

Total Blueprints11

Active Runnable7

Reference Designs4

Test Coverage100%

All Blueprints (11)Active Runnable (7)Architectural Designs (4)

Runtime:All Python Node.js Docker

Architecture Blueprint

Retrieval & Search

Python 3.12+ / PostgreSQL

Production RAG Pipeline (FastAPI + pgvector)

Hybrid retrieval-augmented generation with reciprocal rank fusion and citation verification

Enterprise RAG reference architecture featuring FastAPI, PostgreSQL with pgvector for HNSW vector indexing, BM25 keyword search, reciprocal rank fusion (RRF), and sentence-level citation verification.

Architecture Layers:

Ingress GatewayVector StorageRRF Fusion EngineCitation Guardrail

Prerequisites:

•Python 3.12+
•PostgreSQL 16+ with pgvector extension
•OpenAI or Cohere API Key

Terminal Run Command:click to select all

pip install -r requirements.txt && uvicorn main:app --reload

Reference Repo System Teardown

code-examples/rag-pipeline

Architecture Blueprint

Data Systems & Embeddings

Python 3.12+ / pgvector

Vector Search & Hybrid Retrieval

HNSW and IVFFlat index tuning with pgvector and dense embedding generation

Deep-dive blueprint on vector indexing mechanics. Demonstrates generating dense embeddings, benchmarking HNSW vs. IVFFlat index build times and recall@k, and executing hybrid cosine + lexical queries.

Architecture Layers:

Embedding PipelineVector Index EngineSimilarity Search

Prerequisites:

•Python 3.12+
•PostgreSQL with pgvector
•NumPy / Sentence-Transformers

Terminal Run Command:click to select all

python search.py

Reference Repo System Teardown

code-examples/vector-search

Architecture Blueprint

Agentic Systems

Python 3.12+ / LangGraph

Multi-Step Agent Workflow State Machine

Deterministic cyclic control flow, tool calling, and conditional branching in LangGraph

Architectural blueprint for mission-critical agent workflows. Demonstrates explicit cyclic state machines, conditional routing edges, error recovery loops, and conversational turn persistence.

Architecture Layers:

State MachineControl Flow RouterMemory Persistence

Prerequisites:

•Python 3.12+
•Google Gemini or Anthropic API Key
•LangGraph SDK

Terminal Run Command:click to select all

pip install -r requirements.txt && python workflow.py

Reference Repo System Teardown

code-examples/agent-workflow

Architecture Blueprint

Distributed Agents

Python 3.11+ / LangGraph

Hierarchical Deep Agent Cluster

Distributed multi-agent cluster with delegated sub-graphs and isolated thread state

Scaled enterprise blueprint implementing a hierarchical agent cluster. Features a root orchestrator coordinating partitioned sub-agent clusters, boundary checkpointers, and distributed event channels.

Architecture Layers:

Cluster TopologyDistributed Event ChannelsPartitioned Checkpointing

Prerequisites:

•Python 3.11+
•pip / uv
•Redis or PostgreSQL for distributed checkpointers

Terminal Run Command:click to select all

pip install -r requirements.txt && python cluster.py

Reference Repo System Teardown

code-examples/langgraph-deep-agent-cluster