diff --git a/README.md b/README.md index 1cffda00..0952dbf5 100644 --- a/README.md +++ b/README.md @@ -19,6 +19,12 @@

LLM-supervised persistent memory for AI agents.

+

+ + Mnemon placed sixth with a score of 61.65 in the closed-source Textual Memory track of the 2026 Cycle 2 Agent Memory Leaderboard + +

+ --- LLM agents forget everything between sessions. Context compaction drops critical decisions, cross-session knowledge vanishes, and long conversations push early information out of the window. diff --git a/docs/assets/aml-textual-memory-cycle-2-2026.png b/docs/assets/aml-textual-memory-cycle-2-2026.png new file mode 100644 index 00000000..ef856f4f Binary files /dev/null and b/docs/assets/aml-textual-memory-cycle-2-2026.png differ diff --git a/docs/zh/README.md b/docs/zh/README.md index 6dc9f355..92c82e66 100644 --- a/docs/zh/README.md +++ b/docs/zh/README.md @@ -19,6 +19,12 @@

LLM 智能体的持久记忆系统 — LLM 监督式、钩子集成、四图架构。

+

+ + Mnemon 在 Agent Memory Leaderboard 2026 年第 2 轮文本记忆闭源组获第 6 名,得分 61.65 + +

+ --- LLM 智能体在会话之间会遗忘一切。上下文压缩丢失关键决策,跨会话知识消失,长对话将早期信息推出窗口。