search

crewAIInc / crewAI

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
https://crewai.com
MIT License
21.09k stars 2.93k forks source link

[FEATURE] Support for external memory storage #1218

Open anifort opened 2 months ago

anifort commented 2 months ago

Feature Area

Core functionality

Is your feature request related to a an existing bug? Please link it here.

Enabling memory cannot work when CrewAI application is deployed on a service that supports auto-scaling as the memory data storage files will not be present on new instance creation.

Describe the solution you'd like

Supporting client/server database integration and/or vertor storage integration where the storage is external to the server hosting the crewai application. I deally solution that can use main serverless cloud provider solutions like Vector Search (https://cloud.google.com/vertex-ai/docs/vector-search/quickstart) etc

Describe alternatives you've considered

Sharing drive among multiple instances but not sure how well this will scale and it is not a clean implementation. Additionally if the instance hosting the application dies the files are lost as well (in a serverless environment that storage is not persistent)

Additional context

No response

Willingness to Contribute

I can test the feature once it's implemented

github-actions[bot] commented 1 month ago

This issue is stale because it has been open for 30 days with no activity. Remove stale label or comment or this will be closed in 5 days.

anifort commented 1 month ago

still active feature request

github-actions[bot] commented 3 weeks ago

This issue is stale because it has been open for 30 days with no activity. Remove stale label or comment or this will be closed in 5 days.

anifort commented 3 weeks ago

keep alive