Agentic Architectures

Thirty-five production-grade agentic AI patterns. End to end.

A library and a living textbook — real LLM outputs, provider-agnostic, deterministic-picker discipline throughout, and a comparative benchmark leaderboard that ranks every architecture against every relevant task.

  35   ARCHITECTURES

  283   PASSING TESTS

  17   BENCHMARK TASKS

  9   LLM PROVIDERS

  0   MOCKED RUNS

Overview

A single Python library that packages every major agentic AI pattern from the literature as a runnable Architecture class with a uniform contract. Each pattern ships with a fully executed Jupyter notebook whose theory is written against the captured run — not synthetic examples. The library is multi-provider (Nebius, OpenAI, Anthropic, Groq, Ollama, Together, Fireworks, Mistral, Google) and built on top of LangGraph state machines.

The central technical discipline of the repository is the deterministic-picker pattern — every LLM-as-Scorer surface has the LLM commit to categorical features (booleans, enums) and lets Python compose the deciding signal. This is the universal escape from the LLM-as-Scorer flat-band pathology, applied in 13 of 35 architectures; 9 more are architecturally immune by design.

Quickstart

pip install "agentic-architectures[nebius,faiss,tavily]"

from agentic_architectures import get_llm
from agentic_architectures.architectures import Reflection

arch = Reflection(llm=get_llm(), max_iterations=2, target_score=8)
result = arch.run("Write a haiku about a glacier.")

print(result.output)
print("score:", result.metadata["final_score"], "/ 10")

Same .run(task) interface across all 35 architectures. Same ArchitectureResult return shape. Swap the class, swap the pattern — your downstream code does not change.

Set up a virtualenv from a fresh clone

git clone https://github.com/FareedKhan-dev/all-agentic-architectures
cd all-agentic-architectures

python -m venv .venv
.venv\Scripts\activate              # Windows
source .venv/bin/activate           # macOS / Linux

pip install -e ".[dev,test,docs,nebius,faiss,tavily,networkx]"
cp .env.example .env                # then fill in NEBIUS_API_KEY etc.

pytest -q                           # 283 tests pass in ~30s

Architecture families

Reasoning & Reflection

Self-critique loops that drive answer quality up through iteration.

Reflection · Reflexion · Chain-of-Verification · Self-Discover · Constitutional AI

Sampling & Search

Sample many paths or grow a tree with rewards.

Self-Consistency · Tree of Thoughts · LATS · Mental Loop · Ensemble

Retrieval (RAG)

Ground every claim — five retrieval shapes.

Agentic RAG · Corrective RAG · Self-RAG · Adaptive RAG · GraphRAG

Memory

Learn across calls — pick the storage shape.

Episodic + Semantic · Graph Memory · MemGPT · Voyager · Agent Workflow Memory

Tools & Actions

From one search tool to a real Chromium browser.

Tool Use · ReAct · Planning · PEV · SWE-Agent · BrowserAgent

Multi-Agent

Specialists, debate, multi-perspective research.

Multi-Agent · Blackboard · Debate · STORM · Meta-Controller

Safety & Routing

Categorical actions through deterministic Python gates.

Dry-Run · Reflexive Metacognitive · Computer Use

Specialty

Patterns with a unique shape.

RLHF Self-Improvement · Cellular Automata

Cross-cutting

Patterns that appear across families.

Deterministic-picker · Memory variants

The 35 architectures

Reasoning & Reflection

Sampling & Search

Retrieval (RAG)

Memory

Tools & Actions

Multi-Agent

Safety, Routing & Specialty

Provider compatibility

Provider

Install extra

Notes

Nebius  (default)

[nebius]

Llama-3.3-70B + Qwen3-Thinking; cheapest for the included demos

OpenAI

[openai]

All architectures work; highest quality for reasoning patterns

Anthropic

[anthropic]

Strong on long context; required for production Computer-Use

Groq

[groq]

Fast inference; great for high-volume Self-Consistency

Ollama  (local)

[ollama]

No API key; tool calling depends on the model

Together

[together]

Wide model catalogue

Fireworks

[fireworks]

Function-calling first-class

Mistral

[mistral]

EU-hosted option

Google

[google]

Gemini 2.x via Generative AI API

Switch via LLM_PROVIDER + the corresponding key in .env. No code changes.

Benchmarks

A 17-task suite runs every architecture and scores results. Most recent run, real Nebius Llama-3.3-70B, ~25 min, ~$1.50 in tokens:

Outcome

Architectures

Strong  2/2 or 3/3

Reflection  SelfConsistency  SelfDiscover  BrowserAgent

Perfect on attempted  1/1

21 more — see leaderboard

Pattern-fit failures

LATS on arithmetic (wrong shape) · Debate + Ensemble on Sally trick (group-think) · Reflexion + AWM on raw-fact recall (wrong memory shape)

Overall

33 / 42 correct  78%

Full leaderboard with per-task answer excerpts: docs/benchmarks.md

Learning paths

Four curated reading orders, depending on what you're trying to do.

Path

For

Order

Beginner

Mental model

Reflection → Tool Use → ReAct → Planning → Self-Consistency

RAG-focused

Production retrieval

Agentic RAG → CRAG → Self-RAG → Adaptive RAG → GraphRAG

Multi-agent

Coordination

Multi-Agent → Blackboard → Debate → STORM → Meta-Controller

Safety

Guardrails

Dry-Run → Constitutional AI → Reflexive Metacognitive → BrowserAgent (safety gate)

Star history

Tested

pytest -q
283 passed, 37 skipped (env-gated integration), 1 warning in ~30s

Suite

Coverage

Registry sweep

All 35 architectures (metadata + instantiate + build)

Pure-Python helpers

Haiku checker, composite scorers, subprocess executor, safety gate, sandbox path

Notebook integrity

All 35 notebooks executed, no error outputs, §9 commentary tailored from real captured runs

Integration  (env-gated)

One real-LLM happy-path per architecture, gated via RUN_INTEGRATION=1

Documentation

Contributing

Contributions welcome. Two paths:

1. Add a new architecture — follow the 5-step recipe. The PR template includes a deterministic-picker checklist.
2. Improve an existing one — bug fix, prompt tuning, performance, scoring rubric. Open an issue first to discuss scope.

See CONTRIBUTING.md for the dev setup, code style, and commit-message convention (Conventional Commits — release-please auto-generates the CHANGELOG).

Citation

@misc{khan2026agentic,
  title         = {Agentic Architectures: A Library of 35 Production-Grade Agentic AI Patterns},
  author        = {Khan, Fareed},
  year          = {2026},
  howpublished  = {\url{https://github.com/FareedKhan-dev/all-agentic-architectures}},
  note          = {MIT licensed Python library and runnable textbook}
}

License

MIT — © 2026 Fareed Khan.

Built on LangGraph  ·  Docs powered by Material for MkDocs  ·  Default LLM via Nebius

★ Star  ·  Fork  ·  Open an issue  ·  Discuss