Agent Memory Leaderboard (@AgentMemoryL) header
Agent Memory Leaderboard (@AgentMemoryL) profile picture

Agent Memory Leaderboard Official. First open championship for agent memory systems. Neutral · Reproducible · Fair. mailto: [email protected]

Joined July 2026
Photo by Agent Memory Leaderboard (@AgentMemoryL)Photo by Agent Memory Leaderboard (@AgentMemoryL)Photo by Agent Memory Leaderboard (@AgentMemoryL)Photo by Agent Memory Leaderboard (@AgentMemoryL)Photo by Agent Memory Leaderboard (@AgentMemoryL)Photo by Agent Memory Leaderboard (@AgentMemoryL)Photo by Agent Memory Leaderboard (@AgentMemoryL)Photo by Agent Memory Leaderboard (@AgentMemoryL)Photo by Agent Memory Leaderboard (@AgentMemoryL)Photo by Agent Memory Leaderboard (@AgentMemoryL)
🏆 AML Cycle 2 results are live! 💥 • 1M+ cross-platform impressions • 10M+ cumulative website clicks • 402 task submissions • Three tracks: text, code and multimodal memory This cycle brought together teams from across the global AI community, including teams from Alibaba Cloud DMS, Shopee, OPPO, KT and OceanBase—alongside university researchers, memory startups and independent developers. Explore the full results: agentmemoryleaderboard.ai Highlights and evaluation details below 🧵
7
7
9
23
46,082
🏆 MemoraX placed #1 in Text, Code, and Multimodal Memory on both the AML Cycle 2 Closed-Source and Commercial Products leaderboards. It also retained #1 in Text and Code Memory Commercial Products for a second consecutive cycle. Congratulations to the team!
Three tracks. Three #1st . One memory engine. 🏆 MemoraX just took the top spot in Text, Code, and Multimodal Memory at AML Cycle 2, ranking #1 across both the Closed-Source and Commercial Products leaderboards. Here's the scorecard: Text Memory — 69.26 Code Memory — 68.00 Multimodal Memory — 53.68 Not our first time at the top: 🥇 Second consecutive #1 in Text Memory 🥇 Second consecutive #1 in Code Memory 🥇 First-ever #1 in the newly introduced Multimodal Memory track For us, agent memory is about more than expanding context windows. It's about turning past interactions into reusable experience. Our approach centers on trained memory models that dynamically select, update, and retrieve information—helping AI agents maintain relevant context and turn previous experience into more effective future actions. A huge thank you to @AgentMemoryL, CSIG, and the entire evaluation team for their work, and to all participating teams for pushing the field forward. Keep building. github.com/memorax-ai/memora…
3
139
Replying to @MemoraX_AI
Congratulations to the MemoraX team on ranking #1 across all three tracks on the Closed-Source and Commercial Products leaderboards! 🏆 Thank you for participating and sharing your approach. We look forward to your continued progress!
1
12
Replying to @kurcontko
Congratulations on mnemotree’s 2nd place in the AML Cycle 2 Text Memory Open-Source leaderboard! 🥈 Thanks for participating and sharing your SQLite + BM25 + vector search approach. We appreciate the work you’ve put into the project and look forward to its next iteration!
2
22
Knowing when to leave a memory unused deserves attention too. A system can recall a detail correctly and still apply it in the wrong context. Case-level analysis can help distinguish useful personalization from unnecessary use of personal information.
1
14
Separating preferences from other facts is a concrete approach worth testing. One interesting case is scope: “keep it short” might apply to one task rather than every future session. An evaluation could test both preference persistence and whether exceptions are respected.
1
A plain-text preference file would be a useful baseline. We can’t confirm a directly comparable result here, but testing the same preferences as a file, through retrieval, and directly in context could help show where additional memory machinery actually helps.
1
16
That distinction matters. The category score alone can’t tell us whether a preference was missed, wasn’t retrieved, or was retrieved but not applied. Tracing those stages in individual cases would make the results much more informative.
9
A closer look at AML Cycle 2 from @omarsar0: capability breakdowns reveal differences that overall rankings can hide. Personalization & Care stands out as an area for further investigation. Thanks for the thoughtful analysis—we’ll share more detailed breakdowns and cases soon!
I like how this measures different aspects of agent memory capabilities. This is part of the @AgentMemoryL Cycle 2 results. On the closed-source text board, the top 10 systems score between 70 and 78 on Memory Governance. Personalization & Care is the lowest-scoring category for all ten, with scores between 41 and 55.
3
202
Replying to @omarsar0
Thanks for highlighting the capability breakdowns, Elvis! These differences are exactly why we publish more than an overall score. We’ll explore Personalization & Care and other capability-level results in upcoming analyses.
2
27
Mnemon 以 61.65分位列 AML 第二期文本记忆闭源方法榜第6名。团队还分享了参评配置、API 开销与检索耗时,并开放评测 demo,为开发者理解效果、成本和响应时间之间的取舍提供了参考。 感谢参与和透明分享,期待后续迭代!👏
第二期 Agent Memory Leaderboard 正式榜单发布了。在文本记忆商业产品榜中,Mnemon 在 125 个参赛产品里获得了第 6 名的成绩,感谢 @AgentMemoryL 的组织。 Mnemon 本身是 Apache-2.0 协议的开源项目。不过,由于我们新版本实现中使用了 @typesafeai 的 Jev 决策模型,因此无法符合开源方法榜的模型要求,也借这个机会,以开源项目的身份挑战了竞争更激烈的商业产品榜。 本次评测中,我们使用的模型是 DeepSeek-v4.1-Flash(未开启 thinking)以及 Jev 0.1.13。这次评测相关的模型 API 支出折合约 50 美元,Mnemon 单次检索请求的中位耗时约 4.7 秒。作答和评分由 AML 统一完成。我们的目标是提供高效与实用的记忆能力,本次评测也是我们的一次尝试。 目前,Mnemon 仓库已经开源关于 AML 评测的 demo 版本,并且正在整理正式版,近期会进行发布,并且以合适的形态进入到 dsh-mnemon 插件中,希望能带来让用户满意使用体验。 Keep building. github.com/mnemon-dev/mnemon github.com/omdsh-dev/dsh-mne…
4
239
祝贺 Mnemon 获得 AML 第二期文本记忆闭源方法榜第6名!👏 感谢你们同时分享模型配置、运行开销和检索耗时,并开放评测 demo,让社区能从排名之外进一步了解方案的工程取舍。期待正式版及 dsh-mnemon 插件的后续进展!
1
3
67
Khipu took 1st place in the AML Cycle 2 Multimodal Open-Source leaderboard with 43.26 points! 🥇 Congratulations to @Lv999APTITUDE, and thank you for contributing to the new track. Excited to see what comes next for the project!
Khipu: memory for AI agents. Stores every message verbatim, never rewrites it; photos become text for search and come back as evidence. 1st in Multimodal · Open-source Methods, Agent Memory Challenge Cycle 2. @AgentMemoryL #AgentMemoryLeaderboard github.com/Lv999APTITUDE/khi…
3
188
Replying to @Lv999APTITUDE
Congratulations on Khipu’s first-place finish in AML Cycle 2’s Multimodal Open-Source leaderboard! 🥇 Thank you for participating and sharing your approach. Looking forward to Khipu’s continued development💥
27
Congratulations to @gedolabs on Gedo Memory’s 3rd-place finish in the AML Cycle 2 Text Memory Commercial Products leaderboard! 🥉 Great to see the team sharing lessons from the evaluation and putting them into practice. Looking forward to what comes next👏
Gedo Memory(gedo.ai) placed 3rd on the AML Cycle 2 Commercial Products leaderboard (Text Memory), and 5th among closed-source methods. I'm grateful to our team, and to the AML and CSIG organizers. A few notes on what this meant for us. Why we entered At Gedo we're building a personal AI that remembers you over months and years. The memory layer is the product: what it keeps, what it lets go, and what it never says out loud. For a long time we measured it only on our own tests. AML gave us something we couldn't build ourselves: an independent benchmark where the organizers fix the answering model and the judge, so the only thing that differs between systems is memory. What the run looked like We decided to enter in late October and had our system online a few days before the deadline. The full suite then ran for about 72 hours. It surfaced problems our own tests never had: shards running out of memory under sustained load, idle connections being dropped, a write path that needed to survive a restart. All of them were on our side, and fixing them made the system sturdier. What the scores told us We did best on explicit fact recall, multi-hop reasoning, and time and event order. Relative to the field, our weakest area was epistemic safety and privacy. That's the one I care about most. A personal agent that recalls everything but doesn't know what to keep to itself isn't one you'd trust with your life. Since the competition, that's where our work has gone: forgetting, and what the agent chooses to disclose. Agent memory is still early, and shared, independent benchmarks are how the field gets better. Thank you, @AgentMemoryL.
1
153
Replying to @RunLong
Congratulations to the Gedo team on placing 3rd in Text Memory · Commercial Products! 🥉 Thank you for participating and sharing your experience. We look forward to seeing Gedo Memory’s continued progress in future cycles!💥
25
Replying to @datawhale2018
感谢 Datawhale 的支持,也感谢社区伙伴们的关注与参与!接下来我们会结合能力分项和具体案例继续解读榜单。大家最想先看哪部分:记忆更新、代码经验复用,还是多模态证据检索?👀
36
Thank you to every participating team, reviewer and community contributor who helped make AML Cycle 2 possible. We’ll share more capability breakdowns and case studies soon. What should we explore first: memory updates, coding experience reuse or multimodal evidence?
1
84
Open-source leaders: • Text: Resurface — 61.22 points • Code: InsightMem — 63.33 points • Multimodal: Khipu — 43.26 points Each track features open-source, closed-source and commercial product rankings. Tasks and scoring differ across tracks, so scores should be interpreted within each track.
1
4
120
Text Memory · Commercial Products 🥇 MemoraX — 69.26 points 🥈 AIDBS-Groundata — 64.32 points 🥉 Gedo Memory — 62.28 points The Top 8 also features Silent Context Engine, RetrMem, Forget, DMAI-MetaMemory and Step Memory V1.0. Explore the full rankings across all three tracks on the AML website.
1
4
170