1
华为鸿蒙座舱 HarmonySpace 暑期版本发布，新增导航 Agent 地址主动记忆等功能
IT之家 8 月 30 日消息，华为乾崑智能汽车解决方案昨日分享了 鸿蒙座舱 HarmonySpace 暑期版本 升级亮点。 据介绍，鸿蒙座舱 HarmonySpace 暑期版本在智能交互、座舱玩法和使用体验上进行了升级优化，新 增导航 Agent 地址主动记忆、语音发起导航同时选择路线偏好、多条件…
2
Show HN: Sillage a 4 MB memory that lets a frozen language>model remember
用4MB记忆让冻结的大模型记住新知识，极致压缩且效果惊艳。
Article URL: https://github.com/riscoss63/sillage Comments URL: https://news.ycombinator.com/item?id=49439609 Points: 1 # Comments: 0
3
Claude Cowork finally remembers what you told the app in chat
Claude Cowork终于能记住聊天中的信息了，还默认保护敏感数据，可手动开启个性化记忆。
Anthropic is giving Claude a shared memory across chat and Cowork, so users no longer have to repeatedly brief the AI on projects, preferences, and ot…
4
Anthropic 更新 Claude 记忆机制，打通 Cowork 与聊天的记忆功能
IT之家 8 月 26 日消息，Anthropic 宣布更新 Claude Cowork 与聊天功能之间的记忆机制。此次更新将两个系统的记忆功能打通，实现统一管理。 Anthropic 表示：“Cowork 现在拥有了记忆功能，而且与您在聊天中使用的是同一套记忆。这意味着您无需反复解释背景信息，Cl…
5
MemGuard: Persisting Verifier Signals for LLM-Agent Memory Governance
LLM智能体长任务中记忆失效的痛点，MemGuard用验证信号让存储经验长期可靠。
arXiv:2608.21867v1 Announce Type: new Abstract: LLM agents are moving from single-prompt use to long task streams in which reusable memory becomes a c…
6
The Compaction Cliff in Long-Running AI Agent Memory
安全规则与日志争抢上下文，压缩时规则一字之差即失效，长跑AI智能体记忆悬崖的实证研究
arXiv:2608.22752v1 Announce Type: new Abstract: A safety rule and an episodic log compete for the same tokens in an AI agent's context. When the budge…
7
PrimeAgentOrchestrator: Memory-Primed Agent Spawning for Personal AI Infrastructure
编码代理失忆难题有解了：为新会话预载记忆，让AI助手接续上下文
arXiv:2608.20342v1 Announce Type: new Abstract: Large language model (LLM) coding agents start each session with an empty context window, discarding a…
8
OzBrain's Shared Memory Architecture: How Multi-Agent Teams Avoid Re-Explaining Context Across Sessions
多智能体团队如何通过共享记忆架构告别重复解释上下文，直击协作痛点。
When you run multiple agents across Claude, ChatGPT, and Cursor, each one starts from scratch unless you manually paste context into every session. Oz…
9
Cortex by SKYNETLAB
专为AI打造的记忆层，自动筛选重要信息，让模型记住真正该记的。
The memory layer that decides what's worth remembering Discussion | Link
10
Solving AI Amnesia: Why Your Coding Agents Needs Institutional Memory
一套给 AI 编码代理用的“机构记忆”方案：结构化决策日志 + 哈希校验 + 作用域，让团队上下文不丢。
Solving AI Amnesia: Why Your Coding Agents Needs Institutional Memory Every developer using AI coding agents eventually hits the same wall. You spend …
11
ChatGPT Needs a Better Memory
吐槽ChatGPT记忆功能过度联想，不管问题相关与否都强塞旧内容，引发对AI记忆机制边界的重新审视
ChatGPT needs a better memory, it just try to connect every question with what is there in the memory!! Not only when it is relevant Comments URL: htt…
12
Nvidia just showed that the harness, not the AI model, is now the real hero
别只盯着模型参数，一个调教得当的“缰绳”竟能让Claude Opus 5在推理基准上满分通关。
Nvidia research shows that AI agents can perform well, and not go off the deep end, through fine-tuning, even if the AI model isn't that great at the …
13
Putting mice into hibernation causes a major loss of synapses
冬眠使小鼠突触减半，记忆却能留存，神经科学新发现颠覆认知。
Hibernation cuts down on synapses, but mice seem to retain memories anyway.
14
Can Agent Memory Systems Track Evolving State?
智能体记忆系统能否跟上环境变化，这项研究给出了关键答案与实验验证。
arXiv:2608.19652v1 Announce Type: cross Abstract: As LLM-based agents are deployed for longer and higher-stakes tasks, their memory systems continue t…
15
MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use
大模型记忆中的认知陷阱有了专门的评测基准，帮你识别AI“想当然”的隐患。
arXiv:2608.20202v1 Announce Type: cross Abstract: Memory has become a key component of large language models, enabling them to retain information and …
16
Your Memory API Is Lying to Your Agent
AI记忆并非真相，时间建模才是关键，一文戳破智能体记忆的谎言。
The memory store may know the truth. The interface may be throwing it away. This piece grew out of a conversation on Edward Izgorodin 's post Agent Me…
17
Show HN: Praxos – team messaging with built-in memory
为人和AI代理打造的团队消息平台，内置记忆，打通iMessage、WhatsApp、Slack等多端协作。
Hey HN! What does a regular workflow at a startup look like? Probably like this: > One founder talks to customers > Another founder builds > A custome…
18
Google Discover is getting an AI chatbot-tuned feed
AI 根据聊天偏好实时调整内容流，记住你的喜好，让每次刷新都更懂你。
Google will soon allow you to customize your Discover feed by describing what you want to see. The new feature, rolling out to the Google app in the "…
19
Rune – persistent context for AI coding tools
AI编程助手总忘事？Rune让上下文持久化，代码一变自动更新，新会话可随时查询，开发效率飙升。
Article URL: https://github.com/thecolourfoundation/rune Comments URL: https://news.ycombinator.com/item?id=49359128 Points: 2 # Comments: 0
20
Show HN: Veyra - Self evolving AI agent
自进化AI代理Veyra，从V0种子版本迭代升级，持续优化记忆与架构，打造自主演进系统
Article URL: https://github.com/iondodon/veyra Comments URL: https://news.ycombinator.com/item?id=49358474 Points: 1 # Comments: 0