1
Karpathy LLM Wiki (Obsidian Plugin)
Karpathy的LLM Wiki理念与Obsidian插件结合，打造动态成长的个人知识库，从睡眠健康到AI全覆盖
Article URL: https://llmwiki.greenerai.top/ Comments URL: https://news.ycombinator.com/item?id=48871007 Points: 1 # Comments: 0
2
Ask HN: How do you share agent context across a team?
团队AI agent上下文碎片化？HN热议如何在成员间共享策略、客户笔记等，避免“公司大脑”分裂。
My cofounder and I each run our own Claude Code agent locally. Each has built up real context over time: strategy, customer notes, past decisions, con…
3
Knowledge Atlas by Fini
一个能自动学习并自我改进的知识库，帮你持续构建动态智慧体系。
The self-learning knowledge base that improves itself Discussion | Link
4
Your AI Has No Long-Term Memory. You Need an External Brain
AI没有长期记忆？Karpathy教你用「外部大脑」解决，brain2.wiki就是为此设计的云端方案
Your AI Has No Long-Term Memory. You Need an External Brain How Karpathy-style LLM Wikis, cloud sync, and agent-native APIs are changing the way resea…
5
Show HN: Phileas – Local-first memory that remembers you
本地优先的记忆工具，保护隐私的同时帮你记住一切，开源可自建。
Article URL: https://github.com/alexajuno/phileas Comments URL: https://news.ycombinator.com/item?id=48623929 Points: 2 # Comments: 1
6
Ask HN: What are your best Claude hacks?
用Claude把研究论文变成临时领域专家，这个工作流太聪明了。
One workflow I like: collecting high-quality research papers on a topic, uploading them to Claude, and turning it into a temporary expert on that doma…
7
Least-Action-Guided Diffusion for Physical Extrapolation
输入Arxiv论文链接，快速生成简洁易懂的中文摘要和关键点，适合科研速读。
arXiv:2606.11277v1 Announce Type: new Abstract: Reliable extrapolation remains a central challenge for generative models in computational physics, bec…
8
Infini Memory: Maintainable Topic Documents for Long-Term LLM Agent Memory
提出Infini Memory方法，用可维护主题文档突破LLM Agent长期记忆瓶颈，为持久化知识管理提供新范式。
arXiv:2606.10677v1 Announce Type: new Abstract: Long-term LLM agents need persistent memory that can track changing facts and provide relevant evidenc…
9
NotebookLM’s new update will help you build source repository from chat
从聊天记录自动构建知识源库，支持深度研究模式和Gemini 3.5模型，让研究更高效。
Google is making Gemini 3.5 the default model in NotebookLM
10
Sovereign Synapse: The Local Brain
让海量Markdown文件活起来，变身可对话的本地知识脑，告别静态数字阁楼
A vault of 3,150 Markdown files is just a very organized digital attic. It’s a repository of every conversation, code snippet, and research rabbit hol…
11
Show HN: Kaya Suites – An AI Native Knowledge Base
Rust+Next.js全栈开源AI知识库，轻量部署且灵感源自Langchain的智能文档管理方案。
I'm really interested in this idea of generating a knowledge base that's native for agents as well as humans. I'm pretty much inspired by Den's [ http…
12
13
Mental Models That Change How You Think | Bill Gurley
用双向链接笔记梳理复杂思维模型，Obsidian帮你构建个人知识网络，让历史洞察与技术前沿自然交汇
Bill Gurley spent years on Wall Street, built his career as a partner at Benchmark, worked through Uber’s hypergrowth era, and now serves on the board…
14
Obsidian + VS Code Copilot: Build an AI Second Brain Per Project (Full Setup Guide)
告别杂乱单一大库，手把手教你用Obsidian和Copilot为每个项目打造专属AI第二大脑，提升上下文连贯性。
TL;DR Stop losing context every time you come back to a project. This guide shows you how to set up a per-project Obsidian vault — committed alongside…
15
Show HN: A self-growing wiki of Andrej Karpathy's public work
整合 Andrej Karpathy 公开文章、课程与项目，支持 wiki 浏览和智能问答，每次回答都严格引用来源并自动扩展知识图，让提问等于编辑。
I created one simple place to consolidate all of Karpathy's stuff, like his essays, courses and GitHub projects. You can browse it like a normal wiki,…
16
DMF: A Deterministic Memory Framework for Conversational AI Agents
确定性记忆框架让对话AI不再"失忆"，21页论文详解DMF如何提升对话一致性与可控性。
arXiv:2606.03463v1 Announce Type: new Abstract: Conversational AI agents require memory systems that are both scalable and semantically coherent acros…
17
从插件到 AI 辅助：Obsidian 如何成为我的主力工具
用AI工具武装Obsidian，从插件到智能辅助，手把手教你打造高效知识管理流水线。
我觉得二十一世纪的知识管理工作者，不使用 Obsidian 真的是错过一个亿，真正怎么样还得上手体验了才知道。当我自己慢慢花时间沉浸式使用的时候，明显感觉现在的 Obsidian 真的好用了一倍不止。 查看全文
18
Your Brain Doesn't Have a Paste Button
从信息洪流中只抓真知：如何像心智编辑一样，筛出值得记忆的关键点，而非淹没在琐碎噪音里。
I maintained a file called skippy-context-may.md for months. Four hundred lines of project state, architectural decisions, tool versions, things that …
19
Most enterprise AI projects have the training data they need
企业AI最大障碍不是模型，而是训练数据——从会议转录到业务复盘，知识获取才是关键。
Article URL: https://www.scribeitlocal.com/meeting-transcripts-for-ai-agents.html Comments URL: https://news.ycombinator.com/item?id=48361749 Points: …
20
🤖 The Second Brain 🧠 Playbook 📚 (2026 Edition)
两个框架叠加搞定90%知识工作，2026版第二大脑实操指南。
A practical, no-fluff guide to building an external knowledge system that actually compounds — instead of becoming another graveyard of unread notes. …