ClawVault LoCoMo evaluation

[G9Pedro]

Adds a LoCoMo QA benchmark suite to evaluate ClawVault's memory and retrieval performance against published baselines.

This benchmark suite provides an end-to-end pipeline to ingest LoCoMo conversation histories into ClawVault, perform retrieval and QA, and score answers against gold standards using LoCoMo's official metrics. It enables comparison of ClawVault's filesystem-native approach with competitors and RAG baselines.

  

[cursor]

Cursor Agent can help with this pull request. Just @cursor in comments and I'll start working on changes in this branch.
_{Learn more about Cursor Agents}