[03] Framework/ What thinks

Framework for AI agents

The library you write orchestration in, when an off-the-shelf harness is not enough.

8 options tracked · 8 open source · 8 self-hostable · optional

· All 8 options/ Compare
OptionWhat it doesLicenceSelf-host
LangGraphGraph-shaped orchestration with checkpointing, interrupts and human-in-the-loop.Open sourceYes
MastraTypeScript agent framework with workflows, memory, evals and a local playground.Open sourceYes
Pydantic AIType-safe Python agents with structured output that actually validates.Open sourceYes
CrewAIRole-based crews of agents with delegation between them.Open sourceYes
AgnoFast, lightweight multi-agent runtime with built-in memory and knowledge.Open sourceYes
LlamaIndexData-first framework — ingestion, indexing and RAG-heavy agents.Open sourceYes
DSPyPrograms, not prompts — compile and optimise the prompt against a metric.Open sourceYes
Vercel AI SDKStreaming-first TypeScript SDK with a unified provider interface and UI hooks.Open sourceYes
· Head to head/ 28 comparisons
· Common questions/ FAQ

What is the framework layer of an AI agent?

The library you write orchestration in, when an off-the-shelf harness is not enough. It is optional; plenty of working agents skip it.

How many framework options are there?

This registry tracks 8. 8 are open source and 8 can run on your own infrastructure.

Which framework option should I choose?

It depends on constraints rather than preference: whether you must self-host, whether the budget allows a hosted service, and which language your team writes. Describe what you are building and the advisor fills this layer along with the other 9.

· The other 9 layers/ Keep going
· For agents/ This page, machine-readable

Every page here answers to Accept: text/markdown and returns the same content at roughly a tenth the tokens. No separate site, no toggle — same URL.

curl -s -H "Accept: text/markdown" https://newagent.build/layers/framework