Skip to content
Agents

9 AI agents & agent frameworks

Agents are classified separately from chatbots and models: systems that plan and execute multi-step tasks with tools. Capabilities are editorial classifications from official documentation; autonomy is described, not scored.

Agent capability matrix

#AgentAutonomyBrowserComputerCode execMemoryApprovalFrom
1Model Context ProtocolAnthropic1places upframework–––––OSS
10LangChainLangChain1places downframework–––––OSS
14n8nn8n1places downframework–––––Free
29CrewAICrewAIunchangedframework–––––OSS
36Vercel AI SDKVercel2places upframework–––––OSS
51Claude Agent SDKAnthropic1places upframework–––––OSS
59OpenAI Agents SDKOpenAI2places upframework–––––OSS
72Browser UseBrowser Useunchangedsemi-autonomous✓–––✓OSS
95AutoGenMicrosoft1places upframework–––––OSS

“–” means the capability is not listed in official documentation, not that it is impossible. Security models and task limits: see each agent's official docs (linked on its profile).