Feature request: discuss optional ClawMem-backed memory / knowledge integration

[EricZequan]

Summary

I'd like to discuss whether CrewAI would be open to an optional ClawMem-backed memory integration.

This is not a request to replace CrewAI's architecture. The narrower question is whether ClawMem could fit as an optional memory/knowledge backend for long-running multi-agent workflows.

Why this seems worth discussing

CrewAI's README frames the project as a fast and flexible multi-agent automation framework with:

• multi-agent orchestration
• flows/workflows
• tracing and observability
• seamless integrations
• a unified control plane

That suggests a ClawMem integration could plausibly fit as:

1. an optional memory/knowledge backend
2. an integration package outside core
3. a documented example for durable memory in Crew/Flow setups

What ClawMem would add

ClawMem is oriented around:

• persistent memory across sessions and runs
• auditability of memory changes
• explicit workspace/repository memory boundaries
• optional shared memory across agents and humans

Clarification I am looking for

Would maintainers be open to one of these directions?

1. external integration package
2. docs/example integration
3. first-party optional integration
4. not a good fit for CrewAI

Minimal scope

The smallest useful scope seems to be:

• optional integration only
• no default behavior changes
• focus on durable memory persistence/recall rather than modifying CrewAI core orchestration semantics

If this direction sounds reasonable, I can turn it into a more concrete implementation brief.

[github-actions]

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.