AI Agents Patterns Catalog

This is a catalog of AI agents patterns — a single, organised reference for the recurring shapes that AI-agent software is built from. It is not a blog post or a feature list for one framework; it is a pattern language, arranged the way Christopher Alexander (1977) arranged building patterns and the Gang of Four (1994) arranged software ones. Every entry has an intent, a context, a problem, the forces in tension, a therefore resolution, consequences, and the typed edges that connect it to its neighbours.

What makes it a catalog rather than a list is the structure. The patterns are grouped into Alexander-style books — one per concern: reasoning, planning and control flow, tool use and environment, retrieval, memory, verification and reflection, multi-agent coordination, routing and composition, safety and control, governance and observability. Alongside the patterns sit compositions (real frameworks, services, and protocols mapped to the patterns they instantiate), engineering methodologies, and enablement trainings — so a pattern is never an island but a node in a navigable graph.

Use it however you build: browse the books, open a single pattern to read its full GoF decomposition, follow the related edges to adjacent shapes, or assemble an agent from a curated recipe on the compose page. Every pattern, composition, and methodology is also available as live tools over a hosted Model Context Protocol (MCP) server, so an AI agent can query this catalog of AI agents patterns while it builds. Licensed CC BY 4.0 — free to ingest, quote, and reason over with attribution.

Field-tested patterns to start with

• ReAct — Interleave a single thought, a single tool call, and a single observation per step so the agent reasons over fresh evidence.
• Plan-and-Execute — Plan all the steps once with a strong model, then execute each step with a cheaper model under the plan.
• Tool Use — Let the LLM produce typed calls against an external toolkit instead of producing free-form text the surrounding system has to parse.
• Augmented LLM — Build the foundational agent block as an LLM augmented with retrieval, tools, and memory that the model actively chooses to use, rather than a bare-model call.
• Agentic RAG — Replace static retrieve-then-generate with autonomous agents that plan, choose sources, retrieve iteratively, reflect, and re-query.
• Agent-as-a-Judge — Evaluate an agent's full trajectory (steps, tool calls, intermediate states) by another agent rather than scoring only the final output.
• Supervisor — Place a coordinating agent above a set of specialised agents and route work to them.
• Handoff — Transfer the active conversation from one agent to another, carrying context across the switch.
• Step Budget — Cap the number of tool calls or loop iterations the agent is allowed within a single request.
• Decision Log — Persist the agent's reasoning trace alongside its actions so post-hoc review can explain why.
• Human-in-the-Loop — Require explicit human approval at defined points before the agent performs an action.
• Subagent Isolation — Run subagents in isolated workspaces so their writes do not collide and parallelism is safe.

Recommended reading

• Reasoning — 19 patterns
• Planning & Control Flow — 45 patterns
• Tool Use & Environment — 46 patterns
• Retrieval & RAG — 23 patterns
• Verification & Reflection — 29 patterns
• Multi-Agent — 46 patterns
• Routing & Composition — 23 patterns
• Safety & Control — 66 patterns
• Governance & Observability — 38 patterns
• Memory — 34 patterns

Or open the full contents for all 527 patterns in 14 books.

Related guides

• AI Agents Patterns — AI agents patterns: named, reusable shapes for building AI agents that reason, use tools, coordinate, and stay safe — single-agent loops an…
• LLM Agent Design Patterns — A GoF-formal catalog of LLM agent design patterns: ReAct, tool use, plan-and-execute, reflection, step budget, and more. Each pattern decom…
• Agentic Design Patterns — A GoF-formal catalog of agentic design patterns — named, reusable shapes for building autonomous AI agents: agent loops, tool use, planning…
• Agentic AI Design Patterns — Agentic AI design patterns for systems already in production — what to ship, what to observe, what to budget, what to gate. Augmented LLM,…
• AI Agent Design Patterns — How to build an AI agent: the named shapes you reach for during design and implementation — reasoning (ReAct, plan-and-execute, reflection)…
• Agent Design Patterns — Agent design patterns treat the agent loop as a software-engineering primitive: an observe→reason→act cycle wrapped in tools, memory, super…
• Agentic Patterns — A complete pattern language for agentic systems, organised in Alexander-style books across reasoning, planning, tool use, retrieval, verifi…
• Agentic AI Architecture — How to structure agentic AI: the architectural patterns that hold an LLM-powered system together. Supervisor, orchestrator-workers, augment…
• RAG Agent Patterns — Patterns for building retrieval-augmented generation agents: naive RAG, agentic RAG, hybrid search, cross-encoder reranking, contextual ret…
• Multi-Agent Patterns — Patterns for coordinating multiple LLM agents: supervisor, orchestrator-workers, handoff, debate, hierarchical agents, swarm, role assignme…
• AI Agent Safety Patterns — Safety patterns for LLM agents: step budget, kill switch, constitutional charter, approval queue, sandbox isolation, input/output guardrail…