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…
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
AI代理的记忆不该是死文件柜，Memanto主动整理、查重、淘汰，让每个代理行动前拿到最新简报
Article URL: https://github.com/moorcheh-ai/memanto Comments URL: https://news.ycombinator.com/item?id=49356590 Points: 1 # Comments: 0
长程任务中LLM智能体记忆混乱？这项决策时记忆仲裁机制让智能体精准调用关键信息。
arXiv:2608.02113v1 Announce Type: new Abstract: Large language model (LLM) agents must retain and use cross-step information to act coherently in long…
一个连接即用28个MCP工具，覆盖代码库与项目记忆，让AI开发上下文更清晰高效。
The Problem Model Context Protocol (MCP) lets an AI agent call structured tools instead of guessing from raw text dumped into a context window. Fine i…
跨工具共享的AI记忆库，让Claude Code与Codex无缝衔接，越用越懂你的偏好与历史。
The idea of Wienerdog was born out of my experience setting up my own simple but effective system of memory, self-improving skills and hooks for Claud…
专为个人AI设计的生命周期记忆框架，实现长期上下文感知与个性化交互
arXiv:2607.18975v1 Announce Type: new Abstract: Personal AI is moving beyond chat-only interaction toward continuous services that span phones, cars, …
用AI进行深度角色扮演，通过记忆与Lorebook系统打造沉浸式互动体验
Article URL: https://chatbrat.ai/bratlog/ultimate-ai-roleplay-setup-guide-memory-lorebooks Comments URL: https://news.ycombinator.com/item?id=48877439…
开源自组织记忆工具TRACE，专为LLM代理设计，实现多路径检索与背景树管理，提升代理记忆效率。
Article URL: https://github.com/husain34/TRACE Comments URL: https://news.ycombinator.com/item?id=48829843 Points: 2 # Comments: 0
让大模型像人类一样学习记忆管理，将文件系统操作变为可训练的认知技能
arXiv:2607.01224v1 Announce Type: new Abstract: Memory expertise is a learned skill: knowing what to encode, when to retrieve, and how to organize kno…
一张图讲清AI代理如何用外部记忆避免“失忆”，直击上下文窗口的致命短板。
In this article, we will try to understand how that architecture gets built, from the constraint that forces it to exist all the way to the tradeoffs …
免费工具解决AI记忆文件膨胀问题，堪称Claude用户的救命稻草
I made a memory cleaner for Claude Code. I guess it'll probably work in Codex, OpenCode, Composer etc, but I've only tested it in Claude Code. It's fo…
长周期LLM智能体如何自主决定该记什么？这项研究给出了自适应记忆新方案。
arXiv:2606.21144v1 Announce Type: cross Abstract: Long-term memory systems for Large Language Model (LLM) agents typically try to \emph{remember every…
AI代理记忆管理新方案，免去向量数据库，审计透明，值得关注。
Article URL: https://octamem.com Comments URL: https://news.ycombinator.com/item?id=48628724 Points: 2 # Comments: 0
本地搜索AI编码代理历史，轻松管理每个仓库的决策、陷阱和待办事项，提升开发效率。
Article URL: https://github.com/BetaBots-LLC/callimachus Comments URL: https://news.ycombinator.com/item?id=48613813 Points: 4 # Comments: 2
自托管企业大脑，一键连接所有工具并构建记忆数据库，让AI代理统一查询跨系统数据，无需再手动拼凑信息。
ConnectAI connects and ingests all the data from all of the tools you currently use and makes it queryable by agents. After connecting your tools it w…
在自有Postgres上为AI代理构建源可追溯记忆的开源方案，兼顾隐私与可控性
Article URL: https://github.com/thegoodguysla/myco-brain Comments URL: https://news.ycombinator.com/item?id=48589516 Points: 1 # Comments: 0
这篇文章颠覆了AI代理记忆的主流认知，指出关键不在于容量，而在于权限和语义检索的受控召回。
Most AI Agent Memory discussions start from the same assumption: If the agent forgets, give it more memory. More chat history. More retrieved document…
实测对比Agent记忆的推拉模式，开源项目帮你搞清楚哪个更适合你的AI系统。
Article URL: https://github.com/H-XX-D/recall-memory-substrate Comments URL: https://news.ycombinator.com/item?id=48580203 Points: 1 # Comments: 0
用图结构优化大模型长期对话记忆，效率与连贯性双提升的学术新突破
arXiv:2606.13115v1 Announce Type: cross Abstract: While Large Language Models (LLMs) have advanced open-domain dialogue systems, maintaining long-term…