---
title: "Stacks · GraphCanon"
type: "stack-index"
canonical_url: "https://www.graphcanon.com/stacks"
count: 3
---

# AI stacks & workflows

How the categories fit together to build something real.

- [The RAG stack](/stacks/rag-pipeline.md) - Retrieval-augmented generation grounds an LLM in your own data. A production RAG pipeline is four layers: ingestion, a vector store, orchestration, and evaluation.
- [The AI agent stack](/stacks/autonomous-agent.md) - Autonomous agents plan, call tools, and act over multiple steps. The stack pairs an agent runtime with model tooling, integration glue, and tracing.
- [The local / self-hosted LLM stack](/stacks/local-llm.md) - Running open models yourself for privacy, cost, or control. The stack is a serving runtime, optional fine-tuning, and supporting tooling.

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon/categories`](/api/graphcanon/categories)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)

_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_