面向开发者、研究团队与商业公司的智能体长期记忆系统公开评测。统一 Add / Search 协议，由平台统一执行 Answer 与 Eval。
Measure what your agents remember. Compare what truly matters.
An open evaluation platform for benchmarking Textual, Coding, and Multimodal Memory systems within a standardized, reproducible framework.
Each track keeps its own result table and detailed metric breakdown.
Long-context, persona, script, and conversation-memory benchmarks.
