LangGraph V1 Alpha! 🚀 #957

Closed
opened 2026-02-20 17:42:31 -05:00 by yindo · 5 comments
Owner

Originally created by @sydney-runkle on GitHub (Sep 2, 2025).

Hey LangChain community! LangGraph v1 alpha is out!

We've released v1 alpha versions for langgraph, langchain, langchain-core, and some key integrations packages like langchain-openai and langchain-anthropic.

We're also releasing a new docs site with consolidated open source docs: https://docs.langchain.com/oss/python/langchain-v1.

We've written up a blog post highlighting improvements and changes in these releases: https://blog.langchain.com/langchain-langchain-1-0-alpha-releases/.

LangGraph v1 has no breaking changes compared to our latest v0.6.6, other than the deprecation of create_react_agent, which has moved to langchain.agents and can be used via

from langchain.agents import create_agent

We'd love your feedback! Please try it out with:

uv pip install langgraph==1.0.0a2

We're working on publishing the stable release for 1.0 in late October.

Originally created by @sydney-runkle on GitHub (Sep 2, 2025). Hey LangChain community! LangGraph v1 alpha is out! We've released v1 alpha versions for `langgraph`, `langchain`, `langchain-core`, and some key integrations packages like `langchain-openai` and `langchain-anthropic`. We're also releasing a new docs site with consolidated open source docs: https://docs.langchain.com/oss/python/langchain-v1. We've written up a blog post highlighting improvements and changes in these releases: https://blog.langchain.com/langchain-langchain-1-0-alpha-releases/. LangGraph v1 has no breaking changes compared to our latest v0.6.6, other than the deprecation of `create_react_agent`, which has moved to `langchain.agents` and can be used via ```py from langchain.agents import create_agent ``` We'd love your feedback! Please try it out with: ```shell uv pip install langgraph==1.0.0a2 ``` We're working on publishing the stable release for 1.0 in late October.
yindo closed this issue 2026-02-20 17:42:31 -05:00
Author
Owner

@nicobytes commented on GitHub (Sep 3, 2025):

Hello!

First, congratulations on the amazing v1 alpha release!

I have a question about the difference between AgentState and MessagesState. They appear to be very similar. What are the key differences, and in what cases should we use one over the other?

For context, here are the definitions I'm looking at:

class AgentState(TypedDict):
    messages: Annotated[Sequence[BaseMessage], add_messages]
    remaining_steps: NotRequired[RemainingSteps]

# Example Usage
from langchain.agents import AgentState

class State(AgentState):
    my_var: str
    customer_name: str
class MessagesState(TypedDict):
    messages: Annotated[list[AnyMessage], add_messages]

# Example Usage
from langgraph.graph import MessagesState

class State(MessagesState):
    my_var: str
    customer_name: str

Additionally, it seems that AgentState (with its remaining_steps field) is designed for the new create_agent function. If that's the case, why doesn't it inherit from MessagesState? It seems like a natural extension.

Thanks for your help!

@nicobytes commented on GitHub (Sep 3, 2025): Hello! First, congratulations on the amazing v1 alpha release! I have a question about the difference between `AgentState` and `MessagesState`. They appear to be very similar. What are the key differences, and in what cases should we use one over the other? For context, here are the definitions I'm looking at: ```python class AgentState(TypedDict): messages: Annotated[Sequence[BaseMessage], add_messages] remaining_steps: NotRequired[RemainingSteps] # Example Usage from langchain.agents import AgentState class State(AgentState): my_var: str customer_name: str ``` ```python class MessagesState(TypedDict): messages: Annotated[list[AnyMessage], add_messages] # Example Usage from langgraph.graph import MessagesState class State(MessagesState): my_var: str customer_name: str ``` Additionally, it seems that `AgentState` (with its `remaining_steps` field) is designed for the new `create_agent` function. If that's the case, why doesn't it inherit from `MessagesState`? It seems like a natural extension. Thanks for your help!
Author
Owner

@willianantunes commented on GitHub (Sep 5, 2025):

I'm already testing it. Thank you so much for this amazing library!

By the way, will this issue be fixed? It still occurs using the version 1.0.0a2.

@willianantunes commented on GitHub (Sep 5, 2025): I'm already testing it. Thank you so much for this amazing library! By the way, will [this issue](https://github.com/langchain-ai/langgraph/issues/5891) be fixed? It still occurs using the version [`1.0.0a2`](https://pypi.org/project/langgraph/1.0.0a2/).
Author
Owner

@magallardo commented on GitHub (Sep 6, 2025):

Will this release include capabilities that allow an agent to discover or retrieve a list of other agents running on the same server? This functionality would be very helpful for use cases where agents need to interact with or leverage the capabilities of other agents.

@magallardo commented on GitHub (Sep 6, 2025): Will this release include capabilities that allow an agent to discover or retrieve a list of other agents running on the same server? This functionality would be very helpful for use cases where agents need to interact with or leverage the capabilities of other agents.
Author
Owner

@HaiHui886 commented on GitHub (Sep 11, 2025):

Is there any guide for how to apply A2A in langgraph new version? It will build a agent network.

@HaiHui886 commented on GitHub (Sep 11, 2025): Is there any guide for how to apply A2A in langgraph new version? It will build a agent network.
Author
Owner

@eyurtsev commented on GitHub (Nov 7, 2025):

All released and available in langchain 1.0!

See https://docs.langchain.com/

@eyurtsev commented on GitHub (Nov 7, 2025): All released and available in langchain 1.0! See https://docs.langchain.com/
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/langgraph#957