Get started
Build your first agent, learn the stack, then go deeper.
New here? Three steps:
- Build your first agent β the shortest path to the real ecosystem.
- Architecture at a glance β understand the layers before you dive deep.
- Packages overview β everything that ships under
@agentskit/*.
#What's here
- Getting started β installation, quickstart, first-agent guides.
- Architecture at a glance β ecosystem layers, adoption paths, and how the stack grows.
- Use cases β support agent, research agent, code agent, internal copilot.
- Concepts β the six contracts (Adapter, Tool, Skill, Memory, Retriever, Runtime) + implementations index.
- Comparison β AgentsKit vs LangChain / Vercel AI / Mastra / LlamaIndex.
- Migrating β port from Vercel AI SDK, LangChain.js, Mastra.
- Announcements β release notes + milestones.
- Manifesto β why AgentsKit exists, what it stands for.
#Then pick a tab
- Chat UI β UI
- Autonomous agent β Agents
- RAG / memory β Data
- Production ops β Production
- API lookup β Reference
Explore nearby
- PeerWhich package do I need?
A 5-question decision tree from your use case to the one or two AgentsKit packages you actually need to install.
- PeerArchitecture at a glance
See the AgentsKit ecosystem by layer, how the contracts compose, and how teams usually adopt it over time.
- PeerAgentsKit vs. alternatives
How AgentsKit compares to LangChain.js, Vercel AI SDK, Mastra, and LlamaIndex.js across the surface area that actually matters in production.