Skip to content

TMCRA Agent Memory Engine 2026.07.18

Latest

Choose a tag to compare

@reshuibuduo reshuibuduo released this 18 Jul 10:00

TMCRA is now positioned as an Agent Memory Engine for scope-isolated, source-traceable long-term memory.

Highlights:

  • Publishes the LongMemEval S500 scorecard: 411/500 (82.2%) with six task-level results.
  • Adds English and Chinese architecture and reproduction documentation.
  • Adds the maintained, security-hardened LongMemEval pipeline and benchmark-bound inference checkpoints through Git LFS.
  • Uses the Apache License 2.0.
  • Credits Yu Haoxin as creator and lead developer, with OpenAI Codex credited for development and reproducibility engineering assistance.

See the repository README and CHANGELOG for the complete release scope.