~~It appears that the memory agent is not working.
I have followed the troubleshooting steps in https://www.librechat.ai/docs/features/memory#troubleshooting
I have configured it as follows:
memory:
disabled: false
validKeys:
- "preferences"
- "work_info"
- "personal_info"
- "skills"
- "interests"
- "context"
tokenLimit: 2000
personalize: true
messageWindowSize: 5
agent:
provider: "openAI"
model: "gpt-4.1-mini"
instructions: |
You are a memory management assistant. Store and manage user information accurately.
Delete outdated or incorrect information promptly.
model_parameters:
temperature: 0.25
Memory is enabled in the chat interface (see screenshot). However, no matter what I say, the agent is never triggered, and OpenAI's logs don't show any activity on the configured memory agent model (gpt-4.1-mini).
Using version LibreChat git tag v0.8.2~~
Issue resolved, the config was being rejected due to a duplicate section.