From ae520579417e969004b203e701619e8a40fc2ce8 Mon Sep 17 00:00:00 2001 From: zhuangguomian Date: Wed, 1 Jul 2026 22:40:00 +0800 Subject: [PATCH] docs: update benchmark PR messaging Refresh README benchmark highlights and FAQ with the latest Agent Memory and User Memory evaluation results. Co-authored-by: Cursor --- README.md | 21 +++++++++------------ 1 file changed, 9 insertions(+), 12 deletions(-) diff --git a/README.md b/README.md index c20171832..2bc08cef0 100644 --- a/README.md +++ b/README.md @@ -19,10 +19,10 @@

- ๐ŸŽฏ +43.70% Accuracy vs. OpenAI Memory
- ๐Ÿ† Top-tier Long-term Memory + Personalization
- ๐Ÿ’ฐ Saves 35.24% Memory Tokens
- LoCoMo 75.80 โ€ข LongMemEval +40.43% โ€ข PrefEval-10 +2568% โ€ข PersonaMem +40.75% + ๐Ÿ† Leading Performance Across Agent and User Memory Benchmarks
+ ๐Ÿค– OpenClaw Task Completion Improves from 36.63% to 50.87%
+ ๐ŸŽฏ 92.34 on LoCoMo and 93.40 on LongMemEval
+ ๐Ÿ“Š Unified Evaluation Across 14 Commercial Memory Products @@ -71,6 +71,9 @@ Your lobsters and Hermes Agents now have **the best** memory system โ€” choose * ### News +- **2026-07-02** ยท ๐Ÿ† **MemOS Advances Agent and User Memory Benchmarks** + With MemOS, **OpenClaw** improves average task completion from **36.63% to 50.87%** across five agent tasks. MemOS also achieves **92.34 on LoCoMo** and **93.40 on LongMemEval**, and leads in **OmniMemEval**, a unified evaluation of 14 commercial memory products across ten datasets. + - **2026-05-09** ยท ๐Ÿง  **memos-local-plugin 2.0** Official local memory plugin for **Hermes Agent** and **OpenClaw**. One core powers self-evolving memory across L1 traces, L2 policies, L3 world models, and crystallized Skills, with local-first storage and feedback-driven retrieval. @@ -273,14 +276,8 @@ MemOS is a **Memory Operating System** for LLMs and AI agents that unifies store ### What are the benchmark results? -| Benchmark | MemOS Result | Improvement | -|-----------|--------------|-------------| -| LoCoMo | 75.80 | - | -| LongMemEval | +40.43% vs baseline | - | -| PrefEval-10 | +2568% | - | -| PersonaMem | +40.75% | - | -| **vs OpenAI Memory** | +43.70% Accuracy | - | -| **Token Savings** | 35.24% | - | +MemOS achieves **92.34 on LoCoMo** and **93.40 on LongMemEval** for User Memory, while improving **OpenClaw** average task completion from **36.63% to 50.87%** across five Agent Memory tasks. For details, see [OmniMemEval](https://github.com/MemTensor/OmniMemEval), our unified evaluation framework for benchmarking 14 commercial memory products across ten datasets. + ### How does MemOS compare to other memory solutions?