By using Redis, we’re able to share session context across any number of instances, maintaining continuity and coherence throughout the conversation flow.

Thanks for the contribution.

I don't particularly understand this part: "By using Redis, we’re able to share session context across any number of instances, maintaining continuity and coherence throughout the conversation flow."

Why does a shared memory can avoid the problems you mentioned. Could you help elaborate?

By using Redis, we’re able to share session context across any number of instances, maintaining continuity and coherence throughout the conversation flow.

Thanks for the contribution.

I don't particularly understand this part: "By using Redis, we’re able to share session context across any number of instances, maintaining continuity and coherence throughout the conversation flow."

Why does a shared memory can avoid the problems you mentioned. Could you help elaborate?

Sure

In the first scenario, we have multiple instances of our application running on Cloud Run. Since requests can be routed to any instance, the user context can be lost between messages — potentially causing a looping interaction.

By integrating Redis, we can persist session data and share it across all instances. This allows us to maintain the current session state for each user. Additionally, we can use TTL (Time To Live) to automatically remove expired session data and keep the system clean.

This solution helps in the case of Artificial Nerds to scale agent bots and avoid looped conversations caused by missed context.

Any update on the status of this PR?

Hi, we are preparing a new repo to house community contributions which will give more freedom to the community to add new features that extend ADK's features. Please stay tuned.

Hi, we are preparing a new repo to house community contributions which will give more freedom to the community to add new features that extend ADK's features. Please stay tuned.

Hi Bo! Are there any timeline available for that? We would love to add Redis session storage in our services.

@hangfei do you have an ETA for the community repo?

@boyangsvl this is very important feature to build scalable agents, it would be great, if we get some conclusion soon.

Sorry for the delay. There are some processes we have to go through to create the repo. Please stay tuned.

I really need this kind of solution i'm building big project and i need to share my session between many services.

@boyangsvl any timelines when this feature would be available

Hi folks, could you migrate this PR to our community repo: https://github.com/google/adk-python-community. This work fits very well into domain of that repo. If you have any followup questions, feel free to raise them.

If this Redis Session service is implemented in this new community repository, how will we use it?
I now start our CloudRun app using get_fast_api_app:

from google.adk.cli.fast_api import get_fast_api_app
app = get_fast_api_app(
    agents_dir=AGENT_DIR,
    session_service_uri=SESSION_SERVICE_URI
)

But this session_service_uri argument does not support a URI like "redis://"

How would that work when the community creates other services?

Hi @anoteboom,

I'm thinking about a registry mechanism that allows people to register a session service to a URI schema. Do you have time to think about such a design?