← The AI Systems Map
L0 · LabsFramework / tooling

Agent frameworks (LangChain, LlamaIndex, etc.)

Orchestration layer for RAG and agents

LangChain/LangGraph, LlamaIndex, CrewAI, AutoGen and DSPy are the orchestration frameworks developers use to build RAG pipelines and multi-step agents on top of raw model APIs. They shape how retrieval, memory, tool use and agent control flow are actually wired in production applications.

Examples

LangGraph, LlamaIndex, DSPy

Layer

agent/RAG orchestration

How it fits the stack

Agent frameworks (LangChain, LlamaIndex, etc.) with what it depends on (above) and what it feeds (below). The figure renders as a crawlable diagram and upgrades to an interactive 3D graph as it scrolls into view.

usesusesAgent frameworks(LangChain,LlamaIndex, etc.)LabsModel Context Protocol(MCP)Vector databases
Agent frameworks (LangChain, LlamaIndex, etc.)Depends on ↑

Agent frameworks (LangChain, LlamaIndex, etc.) in the AI stack. Agent frameworks (LangChain, LlamaIndex, etc.) with its immediate upstream dependencies (top) and downstream dependents (bottom) in the AI value chain. Hover a node in 3D, or read the full relationships below.

Graph data (text) — 3 entities, 2 relationships
  • Agent frameworks (LangChain, LlamaIndex, etc.)usesModel Context Protocol (MCP)
  • Agent frameworks (LangChain, LlamaIndex, etc.)usesVector databases