great q! deepagents has more 'batteries included', which langchain v1 is a very minimalistic agent harness if you are doing more complex wor…

great q! deepagents has more "batteries included", which langchain v1 is a very minimalistic agent harness if you are doing more complex workflows (eg claude code for X) -> deepagents if you want something simple -> langchain both are customizable with middleware @hwchase17 @hwchase17 Trying to understand when to use LangChain v1 and when to use DeepAgent. They seem to share many common blocks: middleware, planning, memory summarization, and even skills can be manually added to LangChain. So what should I use for a conversation chat app?

Related

• Deep Agents or @LangChain? Just use the right tool for the right job
• You want a strong opensource and fully customisable harness?! None other than langchain’s deepagents. Try it yourself if in doubt.
• most of the agents we see being built do this the main cases where we see people using 'agent in a sandbox' is when they are using claude ag…
• Deep Agents Deploy: an open alternative to Claude Managed Agents
• Introducing Claude Managed Agents: everything you need to build and deploy agents at scale. It pairs an agent harness tuned for performance …
• This is why you need model agnostic harnesses

Source: Harrison Chase (X) | 2026-04-09