Add Weaviate Engram Memory Agent Example

Summary

Add an agent memory example using Weaviate Engram for persistent, scoped, and searchable long-term memory.

Proposed location

memory_agents/weaviate_engram_memory_agent/

What to build

Create a runnable memory-agent example that stores useful facts from user interactions in Weaviate Engram and recalls relevant memories in later conversations.

The example should show memory capture, semantic memory search, user/session scoping, memory updates or reconciliation behavior, and fallback behavior when memory is unavailable. It should focus on a concrete use case such as a technical support assistant, account manager assistant, or project continuity agent, and follow the repository's existing Nebius Token Factory configuration pattern for model calls.

Acceptance criteria

• Includes a README.md based on .github/README_TEMPLATE.md.
• Uses Weaviate Engram through the Python SDK or REST API.
• Demonstrates storing memories from conversation or event input.
• Demonstrates searching and recalling relevant memories in a later turn.
• Shows user/session scoping so memories do not leak across users.
• Handles unavailable Engram credentials or API failures gracefully.
• Includes .env.example with no secrets and required Engram/model configuration.
• Adds one catalog entry to the root README.md under Memory Agents.

Contribution notes

Please keep this to one self-contained project and one pull request. Link the pull request with Closes #<issue-number>.