1
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…
2
ContextMemory v0.1.0-beta: what shipped
Agent memory 新玩法：像维基百科一样可浏览的 AI 记忆，告别向量黑盒与 RAG 注入，还新增 Cursor 风格 HTTP、视觉、PDF 等 Agent 工具。
ContextMemory v0.1.0-beta is out. Agent memory you can open like a wiki — not a vector black box, not classic RAG inject. Release notes ## 0.1.0-beta…
3
Useful Agent memory for Your Openclaw and Hermes Agent🔥
探索Openclaw与Hermes Agent的实用记忆功能，提升智能体表现。
Building a Hermes Memory Plugin for a Voice-Powered Conference Agent with Weaviate Engram🧠 Astrodevil Astrodevil Astrodevil Follow Jun 17 Building a H…
4
Are We Ready For An Agent-Native Memory System?
Agent原生记忆系统是否已就绪？多位作者前瞻探讨AI记忆架构的演进方向，值得关注。
arXiv:2606.24775v1 Announce Type: new Abstract: Memory for large language model (LLM) agents has rapidly evolved from simple retrieval-augmented mecha…
5
Show HN: FERNme – agent memory that updates with ~zero LLM calls
无需LLM调用的Agent记忆层，利用Hebbian规则与模糊偏好图实现低成本、类脑的持久记忆更新。
Hi HN, FERNme is a memory layer for AI agents. Most systems (Mem0, etc.) call an LLM on every turn to extract/summarize memory, or dump everything int…
6
Show HN: Push vs. Pull Agent Memory?
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
7
MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing
AI智能体记忆系统新突破：分层时间索引实现高效检索，专为长时间任务优化。
arXiv:2605.23986v1 Announce Type: cross Abstract: Memory is a fundamental component for enabling long-context LLM agents, supporting persistent state …