HackerNews中文版

我一直看到开发者（包括我自己）都在为同一个问题而苦恼：“我需要多个‘第二大脑’来处理我生活的不同方面，但 AI 却总是在会话之间忘记上下文。” 所以我构建了 llmswap v5.1.0，它拥有一个工作区系统，可以为你提供持久的、针对每个项目的 AI 记忆。它的工作原理如下： ``` - cd ~/work/api-platform → AI 加载企业模式、团队规范 - cd ~/learning/rust → AI 加载你的学习旅程，以及你在哪里遇到了困难 - cd ~/personal/side-project → AI 加载个人偏好、实验 ``` 每个工作区都有独立的记忆（context.md, learnings.md, decisions.md），这些记忆会在会话之间保持不变。你的 AI 导师实际上会记住你昨天、上周、上个月学到的东西。主要功能： ``` • 自动学习日志（AI 从每次对话中提取关键学习内容） • 6 种教学角色（在 Guru、Socrates、Coach 之间切换，以获得不同的视角） • 适用于任何提供商（Claude Sonnet 4.5, IBM Watsonx, GPT-4 o1, Gemini, Groq, Ollama） • Python SDK + CLI 集于一体的工具 • 零供应商锁定 ``` 可以把它想象成“LLM 的 cURL”——通用、简单、强大。工作区系统是它与众不同的地方。没有竞争对手（Claude Code, Cursor, Continue.dev）拥有带有自动学习跟踪功能的、针对每个项目的持久记忆。专为以下开发者打造： ``` - 管理多个项目并经常丢失上下文切换 - 厌倦了每次会话都重新解释他们的技术栈 - 希望 AI 能够基于之前的学习成果进行构建，而不是从零开始 - 需要针对工作/学习/副业的不同“模式” ``` 欢迎反馈！特别感兴趣的是： ``` 1. 还有哪些工作区功能会很有用？ 2. 你目前是如何跨项目管理 AI 上下文的？ 3. 你会使用自动学习日志吗？ ``` GitHub: https://github.com/sreenathmmenon/llmswap PyPI: pip install llmswap==5.1.0 文档: https://llmswap.org

查看原文

I kept seeing developers (including myself) struggle with the same problem: "I need multiple second brains for different aspects of my life, but AI keeps forgetting context between sessions."So I built llmswap v5.1.0 with a workspace system that gives you persistent, per-project AI memory.How it works:<pre><code> - cd ~/work/api-platform → AI loads enterprise patterns, team conventions - cd ~/learning/rust → AI loads your learning journey, where you struggled - cd ~/personal/side-project → AI loads personal preferences, experiments </code></pre> Each workspace has independent memory (context.md, learnings.md, decisions.md) that persists across sessions. Your AI mentor actually remembers what you learned yesterday, last week, last month.Key features:<pre><code> • Auto-learning journals (AI extracts key learnings from every conversation) • 6 teaching personas (rotate between Guru, Socrates, Coach for different perspectives) • Works with ANY provider (Claude Sonnet 4.5, IBM Watsonx, GPT-4 o1, Gemini, Groq, Ollama) • Python SDK + CLI in one tool • Zero vendor lock-in </code></pre> Think of it as "cURL for LLMs" - universal, simple, powerful.The workspace system is what makes this different. No competitor (Claude Code, Cursor, Continue.dev) has per-project persistent memory with auto-learning tracking.Built for developers who:<pre><code> - Manage multiple projects and lose context switching - Are tired of re-explaining their tech stack every session - Want AI that builds on previous learnings, not starts from zero - Need different "modes" for work/learning/side projects </code></pre> Open to feedback! Especially interested in:<pre><code> 1. What other workspace features would be useful? 2. How do you currently manage AI context across projects? 3. Would you use auto-learning journals? </code></pre> GitHub: https://github.com/sreenathmmenon/llmswapPyPI: pip install llmswap==5.1.0Docs: https://llmswap.org

Show HN: Llmswap – 用基于项目的 AI 记忆解决“多重第二大脑”问题