Hey LangChain Community!
We’re excited to announce that we’ve published the first alpha release for LangChain & LangGraph v1! There are a few key points:
LangGraph is largely the same as before, no breaking changes. We’ve heard good feedback about LangGraph and are excited to move to 1.0
New standard content blocks on messages in LangChain Core. Message formats are evolving, and so is LangChain. Backwards compatible
LangChain itself - high level agents and chains - is greatly changed. You should think of LangChain 1.0 as a new package - focused around a central agent abstraction, built on top of LangGraph
New docs site!
Note that these are alpha releases (and docs), so you can expect some rough edges and breaking changes throughout the alpha period (if you encounter any issues, please open an issue!). We’re working on publishing the stable release for 1.0 in late October. To get started with v1, head on over to the quickstart guide or read the blog post
Tik1993
September 2, 2025, 6:34pm
2
I’m excited for v1 and to see how it applies to my application!
Really great to hear v1
What a great moment it is
Have beenfollowing and a avid user from v0.0.1 to create-react agent move from langchain to langraph to langmem and bigtols and supervisor agents to init chat model and finally now
What a journey
Wish to continue to be a part of your community
With lots of enthusiasm,
All the best
Shriram
Final year Student
samushi
September 5, 2025, 1:06pm
4
As a Senior PHP Engineer with extensive experience in building large-scale web applications, I’m curious to know how feasible it is to build frameworks similar to LangChain and LangGraph in PHP. Considering PHP’s ecosystem, concurrency model, and integration capabilities, do you see realistic opportunities for implementing such agentic workflows and graph-based orchestration in PHP, or would it be more practical to interface with existing Python/TypeScript implementations instead?
Hi!
I wonder if this issues will be addressed for the 1.0 release?
opened 01:22AM - 01 Aug 25 UTC
bug
pending
### Checked other resources
- [x] This is a bug, not a usage question. For ques… tions, please use the LangChain Forum (https://forum.langchain.com/).
- [x] I added a clear and detailed title that summarizes the issue.
- [x] I read what a minimal reproducible example is (https://stackoverflow.com/help/minimal-reproducible-example).
- [x] I included a self-contained, minimal example that demonstrates the issue INCLUDING all the relevant imports. The code run AS IS to reproduce the issue.
### Example Code
```python
### **Steps to Reproduce**
1. **Create a `checkpoint_config.py` file to configure an SQLite checkpointer:**
# checkpoint_config.py
import aiosqlite
from langgraph.checkpoint.sqlite.aio import AsyncSqliteSaver
async def get_sqlite_saver():
# Ensure the database connection is awaitable
conn = await aiosqlite.connect("checkpoint.db")
return AsyncSqliteSaver(conn=conn)
2. **Create a `my_graph.py` file defining a simple graph and configuring it with the SQLite checkpointer:**
# my_graph.py
from typing import TypedDict
from langgraph.graph import StateGraph
from checkpoint_config import get_sqlite_saver
class State(TypedDict):
value: int
def step(state: State):
print(f"Current value: {state['value']}")
return {"value": state["value"] + 1}
async def get_graph():
builder = StateGraph(State)
builder.add_node("step", step)
builder.set_entry_point("step")
builder.add_edge("step", "step")
# Configure the persistent SQLite checkpointer
checkpointer = await get_sqlite_saver()
print(f"Graph compiled with checkpointer: {checkpointer}")
graph = builder.compile(checkpointer=checkpointer)
return graph
3. **Create a `langgraph.json` file pointing to the graph:**
{
"graphs": {
"my_agent": "./my_graph.py:get_graph"
}
}
4. **Start the service using `langgraph dev`:**
langgraph dev --port 8088
5. **Interact with the service to create some state changes.** For instance, call `ainvoke` several times via the LangGraph Studio or `curl`.
6. **Restart the `langgraph dev` service.**
```
### Error Message and Stack Trace (if applicable)
```shell
### **Expected Behavior**
After restarting the service, the previous conversation state should be fully preserved and loaded, as the checkpointer is configured to use `checkpoint.db`. The `checkpoint.db` file should contain data records.
### **Actual Behavior**
After restarting, all conversation state is lost. Although the `checkpoint.db` file is created, it remains empty. The startup logs from `langgraph dev` clearly indicate that it is using an in-memory runtime:
`[info] Using langgraph_runtime_inmem`
`[info] Starting In-Memory runtime ...`
```
### Description
### **Problem Description**
When using the `langgraph dev` command for development, we've observed that it ignores any persistent checkpointer (e.g., `AsyncSqliteSaver`) configured in the code for a graph. Instead, it forcibly uses a temporary in-memory runtime (`langgraph_runtime_inmem`). This results in the loss of all conversation state upon server restart, which significantly complicates the development and debugging of state-dependent agents.
We expect `langgraph dev` to either respect the checkpointer configured in the code, similar to when running a script directly, or at least provide a command-line option to enable persistence.
### **Expected Behavior**
After restarting the service, the previous conversation state should be fully preserved and loaded, as the checkpointer is configured to use `checkpoint.db`. The `checkpoint.db` file should contain data records.
### **Actual Behavior**
After restarting, all conversation state is lost. Although the `checkpoint.db` file is created, it remains empty. The startup logs from `langgraph dev` clearly indicate that it is using an in-memory runtime:
`[info] Using langgraph_runtime_inmem`
`[info] Starting In-Memory runtime ...`
This demonstrates that the `builder.compile(checkpointer=checkpointer)` configuration in the code is completely ignored by `langgraph dev`.
### **Additional Context**
We have carefully checked our local environment configuration and reviewed the official LangGraph documentation but have been unable to find any instructions on how to enable persistent storage for `langgraph dev`. We also noticed that even when no checkpointer is provided in the code, `langgraph dev` does not use the `.langgraph_api` directory for state persistence as one might expect; the files in that directory are not updated as the conversation progresses. This further reinforces our conclusion that `langgraph dev` may currently be hardcoded to run in-memory, bypassing all persistence mechanisms.
While we understand that `langgraph dev` is intended as a development tool, this behavior makes it very difficult to develop complex conversational agents that rely on persistent state. Every code change that triggers a hot reload forces us to recreate the conversation state from scratch, which severely impacts development efficiency.
If this is indeed the intended behavior of `langgraph dev`, we would appreciate it if this were clarified in the official documentation. If it is a configurable issue, we would be grateful for guidance on how to resolve it. Thank you!
### System Info
### **Environment Information**
* **LangGraph Version:** 0.6.1
* **Python Version:** 3.12
* **Operating System:** Windows
langgraph dev --port 8088 --no-browser
I loooove the work you guys are doing! Great progress!
Do you plan to upgrade the ui repo?
The LangGraph Studio Interact view does not show subagents work.
I’d would be super great if you could show some advanced techniques on how to implement memory
I like that you have your own academy. I would also love to hear more about deep agent best practices.
And ambient agent best practices.
Keep doing the great work!
caspar
October 9, 2025, 6:06pm
10
Hi @beepsoft -langgraph dev is strictly for development and so it is by design that langgraph api will use an in-memory checkpointer. We have no plans to support alternative checkpointers here. If you want persistent storage you can deploy on LangGraph Platform, where you have a few deployment options: see the docs .
I’d be interested in playing with existing agents , where can I find some ? The ones from the CLI seem to be using the old versions still.
Etienne
October 10, 2025, 2:48pm
12
it’s great : there is everything I was waiting for!
Love to have LangChain Alpha access in LangSmith deployments, at least for development
