Skip to content
Library  ·  Textbook  ·  Benchmark

The complete library of agentic AI patterns.

Thirty-five production-grade architectures, built on LangGraph. Real LLM outputs end-to-end, provider-agnostic, deterministic-picker discipline throughout — and a benchmark that ranks them all.

35
Architectures
283
Passing tests
17
Benchmark tasks
9
LLM providers

Living textbook

Every notebook's commentary quotes the actual captured run — not a synthetic example. Theory written against observed behavior.

Deterministic picker

Every LLM-as-Scorer surface uses a categorical commitment + Python composition. No flat-band pathology, by design.

Provider agnostic

One get_llm() factory speaks Nebius, OpenAI, Anthropic, Groq, Ollama, Together, Fireworks, Mistral, Google.

Comparable

A 17-task benchmark suite runs every architecture and scores results. See which pattern suits which task family.

Eight families. Thirty-five patterns.

Reasoning & Reflection

Reflect, verify, revise.

Self-critique loops that drive answer quality up through iteration. Catch hallucinations before they ship.Reflection · Reflexion · Chain-of-Verification · Self-Discover · Constitutional AI
Sampling & Search

Many paths, one answer.

Sample N reasoning trajectories and pick the modal answer; or grow a tree and search it with rewards.Self-Consistency · Tree of Thoughts · LATS · Mental Loop
Retrieval (RAG)

Ground every claim.

Five distinct retrieval shapes — from agent-decides-when, to corrective grading, to graph community summaries.Agentic RAG · Corrective RAG · Self-RAG · Adaptive RAG · GraphRAG
Memory

Learn across calls.

Episodic reflections, archival skills, OS-style tiered context, mined workflows — pick the right shape for your task.Episodic + Semantic · MemGPT · Voyager · Agent Workflow Memory
Tools & Actions

Act on the world.

From a single search tool to a sandboxed code repo to a real Chromium browser.Tool Use · ReAct · Planning · PEV · SWE-Agent · BrowserAgent
Multi-Agent

Coordinate many minds.

Specialists, debate, ensembles, multi-perspective research. Beyond the single-agent loop.Multi-Agent · Blackboard · Ensemble · Debate · STORM
Safety & Routing

Block before harm.

Categorical actions through deterministic Python gates. Meta-control over a roster of specialists.Dry-Run · Reflexive Metacognitive · Meta-Controller · Computer Use

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())
result = arch.run("Write a haiku about the sea.")
print(result.output)
print("score:", result.metadata["final_score"], "/ 10")

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

Start building.

Pick an architecture, paste a snippet, ship.