hermes - 💡(How to fix) Fix [Feature]: multiple users per agent with separated context

Problem or Use Case

Dear Nous Research team,

We hope you are all doing great and congrats for shipping a great product to the world!

We are a small start-up of 4 people looking forward to integrating the Hermes agent into our product, an AI administrative assistant. However, in order to do this efficiently, we would need support for a use case that is not supported at the moment. While we've built our own MCP and tools to connect to the Hermes agent, what we would ideally like is the possibility of having a single instance of Hermes to serve requests to multiple users, while keeping the context separate for each user. We need a secure way of keeping the contexts separate to ensure the privacy of each user. To do this, we were thinking about having each user's context inside a database, so that each time a user sends a message to the agent, we can retrieve the right context from the database and send it to the agent together with the user's message.

We would appreciate it if you could let us know whether you were/are planning to implement this architecture to support such a use case in the short term. If that's not your priority, while you believe there is value in this functionality, we would be open to collaborating with you in bringing this feature to the Hermes agent.

Please let us know what your thoughts are on this.

Thank you for providing such a great tool to the open source community.

Best regards,

PS: Apologies if this is not the right channel to connect, we couldn't find a communication channel dedicated to inquiries like this.

Proposed Solution

Plan the addition of this feature or discuss about collaborating in its implementation.

Alternatives Considered

No response

Feature Type

New tool

Scope

None

Contribution

• I'd like to implement this myself and submit a PR

Debug Report (optional)