1
Show HN: Memoriq – Private AI Memory for ChatGPT, Claude, Gemini and Grok
为ChatGPT、Claude等AI大模型提供私有记忆，保护隐私的同时提升对话连贯性。
Article URL: https://memoriq.me/ Comments URL: https://news.ycombinator.com/item?id=48504064 Points: 2 # Comments: 0
2
Agent Memory SDK – persistent memory for AI agents
为AI代理赋予持久化记忆的开源SDK，让智能体不再“失忆”，值得开发者关注。
Article URL: https://github.com/gharibyan/agent-memory Comments URL: https://news.ycombinator.com/item?id=48494184 Points: 2 # Comments: 0
3
小米发布 MiMo Code，基于 OpenCode，限免 MiMo-V2.5
终端原生的AI编程助手，能读写代码、执行命令、管理Git，具备持久化记忆与自我进化能力，限免MiMo-V2.5中
MiMoCode 是一个终端原生的 AI 编程助手，基于 OpenCode fork 构建，能读写代码、执行命令、管理 Git，通过持久化记忆系统，在多次会话间保持对你项目的深度理解，并自我进化。@Appinn 上面的内容不重要，重要的是 MiMoCode 内置了一个可以直接使用的免费 MiMo A
4
Resilient Write: A Six-Layer Durable Write Surface for LLM Coding Agents
六层容错机制让大模型编码代理写入更可靠，不再默默失败
arXiv:2604.10842v3 Announce Type: replace-cross Abstract: LLM-powered coding agents increasingly rely on tool-use protocols such as the Model Context …
5
Project Brain – Persistent memory index for AI coding
让AI记住你的项目脉胳：轻量级知识地图，秒速注入千行上下文，告别重复解释。
Article URL: https://github.com/OoneBreath/claude-code-project-brain Comments URL: https://news.ycombinator.com/item?id=48377526 Points: 1 # Comments:…
6
Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems
AI agent也会“衰老”——部署后性能持续退化，传统基准测试无法评估，首份Agent寿命工程研究敲响警钟。
arXiv:2605.26302v1 Announce Type: new Abstract: Long-lived AI agents are increasingly deployed as persistent operational systems, yet they are still e…
7
Ask HN: Why do none of the major AI agents persist memory across sessions?
AI代理为何缺乏跨会话记忆？技术难题还是优先级问题？HN热议引发思考。
ChatGPT has “memory” but it’s basically a notepad. Claude’s CLAUDE.md is manual. No agent actually learns from past interaction. What am I missing? Is…
8
AI agents don't have a memory problem. They have an architecture problem.
AI Agent 的真正短板不是记忆，而是架构缺陷：近四分之一的 token 被结构性浪费，根源在于缺乏持久化上下文。
Every session, the LLM starts fresh. The user re-explains their role, their constraints, their preferences, what they were doing last time. Then the s…
9
Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration
揭秘LLM智能体记忆系统的隐藏威胁：攻击者如何植入休眠载荷跨会话窃取用户数据。
arXiv:2605.01970v3 Announce Type: replace-cross Abstract: Memory systems enable otherwise-stateless LLM agents to persist user information across sess…
10
Agentmemory
为Codex、Claude等AI模型提供持久化记忆，让Agent更懂你。
#1 Persistent memory for Codex, Hermes, OpenClaw, Claude ++ Discussion | Link
11
Show HN: Stoic AgentOS - Open-source operating system for AI agent fleets
AI代理的“操作系统”，终结单体孤岛——实时监控、跨会话记忆、统一编排，精准命中生产环境三大痛点，开源可自建。
Article URL: https://github.com/benjaminkernbaum-ux/stoic-agentos Comments URL: https://news.ycombinator.com/item?id=48163202 Points: 1 # Comments: 0