最近看到，MemOS 团队开源了一个拥有超强记忆的模型 MemT 1.0，想让模型把经验记在内部，做任务时再调用出来。
This is a dev post classified by AGK Intelligence as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
最近看到，MemOS 团队开源了一个拥有超强记忆的模型 MemT 1.0，想让模型把经验记在内部，做任务时再调用出来。 让它修 Bug 时，可以先整理好过去处理类似问题的经验。等模型卡住，再把相关经验写进记忆，让它接着往下做。 在 SWE-bench Verified 上，每道修复题让模型独立跑三次。没有补充经验时，三次都修对的题目占 54%；卡住时写入经验，这个比例提到了 62.8%。 这些经验不用一直放在对话上下文里。MemT 的记忆状态大小也是固定的，对话变长后不会跟着不断膨胀。 目前 Nano 和 Flash 两个模型的权重均已开源，Nano 两张显卡就能跑。 Hugging Face：https://huggingface.co/collections/MemTensor/memt-1
Posted by GitHubDaily (90.6k followers) 2 days ago · 9 likes · 3.6k views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: memtensor.
More dev work like this
- 🎃Dario给中国人民带来的极致恐怖从Claude无情封号开始 — @NFT_Chen
- Mia's Qwen3.8-Flash-Next recipe on a DGX Spark: one command, first try, 2 min to the… — @niklaslenz_ai
- 给AI喂一整仓，最烦的就是它每回都从头翻文件，这毛病你多半也遇到过。 — @bkdgiffug
- Coding agents aren't slow because they're dumb. They're slow because every edit waits on… — @RunAnywhereAI
- ICYMI: Foursquare co-founder @dens sat down with our Head of Product, AI, Jeff Smith at… — @automattic
- 🤯惊了！9B参数大模型，只需16G内存即可本地跑通，能力反超Qwen3.5-27B！ — @NFT_Chen
- Introducing JetSpec++: we find causal parallel drafting paired with hidden states… — @haoailab
- Build the agent, test the agent, grade the results, change the agent, run the test cases… — @rseroter
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.2k posts from 5k X accounts over the last 21 days, 8.8k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-10-30 20:27 UTC. Full method.