Skip to content

#Context/memory

0 items today
10/5Mon
10/4Sun
  1. 佬刘AI78

    Planning with GPT, Execution with DeepSeek: A Cost-Saving Two-Model Workflow

    The author has GPT (gpt-6.1-sol, reasoning tier high) handle planning, key decisions, and acceptance in Codex, and calls DeepSeek-V4.1-Flash through the official DeepSeek Harness to write code, run experiments, and fix bugs—together producing a local PDF toolkit with five working features.

    Why it matters: The author splits the work between GPT for planning and DeepSeek for execution to get a PDF toolkit running, and shares three prompts plus cache usage data that can carry over to cutting costs on long tasks.

10/3Sat
  2. TonyBai80

    Pi 1.0 is out: the Agent engine behind OpenClaw now takes in MCP and ships Pi Durable with crash recovery

    On October 1, the Earendil team released the Agent Harness Pi 1.0, with roughly 11.1 stars and 1.4 forks on GitHub, plus an experimental new package called Pi Durable.

    Why it matters: Pi 1.0 and Pi Durable bring distributed concepts like checkpoints, idempotent commits, and ownership trees into the Agent runtime, which you can use to weigh the engineering trade-offs of long-running Agents.

  3. Cursor Forum · Showcase60

    Pinpoint：点击页面元素并说明改动，Cursor 即可获得上下文

    作者因厌倦粘贴截图和用文字描述“左边第三个按钮”，开发了 Pinpoint，一个本地 MCP server 加 Chrome 扩展。在开发站点点击元素并输入要改的内容后，Cursor 会收到评论以及选择器、DOM 路径、计算样式、React/Vue 组件链、源文件提示和该元素的裁剪截图。

    Awaiting translation

10/2Fri
10/1Thu
9/30Wed
  1. 老刘说NLP38

    Personal Agent 个人智能体总结：是什么、为什么、怎么做、应用场景及一些限制？

    Personal Agent（个人智能体）被定义为持久记忆+工具执行+目标规划、以个体为中心的代理系统，是交互范式从"问—答"到"交代—办成"的迁移。其热度源于记忆基础设施成熟、MCP 标准化与模型同质化下的入口焦虑，工程重心在记忆质量、上下文工程与可靠性三处，开源侧可用 OpenClaw+Mem0+MCP 快速拼出原型。

    Awaiting translation

  4. Hacker News · AI 编程经验问答38

    Ask HN：AI 编程智能体用量超限时如何切换而不丢上下文？

    一位开发者询问如何在 Codex 与 Claude Code 等 AI 编程智能体之间切换，以应对单个工具的用量限制，核心诉求是切换时不丢失正在进行的上下文和任务。他表示找到的少数方案都缺乏关注度，并说明自己目前无法承担从每个智能体每月 20 美元涨到 100-200 美元的套餐升级。

    Awaiting translation

9/29Tue
  2. Habr · Claude Code82

    A Product Designer Went Solo with Claude Code for a Month: What I Built Around the AI to Keep the Project from Falling Apart

    A product designer with six years of SaaS experience used Claude Code to single-handedly build Котомка, a life-planning app. Nearly all the code was written by AI; his job was to define requirements, review the results, and make decisions.

    Why it matters: Using a real repository, the author documented the pitfalls he hit while building a product on Claude Code alone, plus the rules, hooks, and testing guardrails he set up around the AI.

  3. 沉默王二75

    Claude Opus 5.5 提示词指南实践：删掉 think carefully、按任务调 effort

    作者根据 Claude 官方新出的提示词指南，整理出在 Claude Code 中使用 Opus 5.5 的几条做法。官方称 Opus 5.5 每次回复前都会自行决定思考多少，删掉提示词里的 think carefully 后回复更早且质量没有下降，作者用 grep 命令清理了 CLAUDE.md、rules 和 Skill 中的这类指令。

    Awaiting translation

9/28Mon
  2. 袋鼠帝AI客栈22

    体验国内首款个人AI助理 Today：基础版永久免费，新用户送1亿token

    国内首款个人AI助理 Today 中国版已正式上线，基础版永久免费，新注册用户可领 1 亿 token 和 1 个月 Pro 会员。作者基于 Today 搭建的个人助理“毛肚”接入本地文件夹、X、GitHub 和 Gmail 作为上下文，能主动提醒积压 17 天的 PR、按账号调性找选题并自动发布推文。

    Awaiting translation

  3. AI产品阿颖38

    国内 Personal Agent 产品 Today AI 发布，可连接飞书、钉钉、Linear

    国内 Personal Agent 产品 Today AI 发布，可连接飞书、钉钉、Linear 等应用获取个人 Context，主动发现并推进任务，而非等待用户输入 Prompt，发布期可免费领取一亿 Token。作者认为它与 Meta Muse 同属 OpenClaw 思路的延续，差别在于把记忆做成产品层，让 Agent 从对话框转向主动协作。

    Awaiting translation

9/27Sun
9/26Sat
  1. Sean Goedecke · Blog38

    给初级软件工程师的建议：AI 时代不要恐慌，也别把判断力交给 AI

    面对 LLM 和 AI 智能体带来的行业剧变，资深工程师 Sean Goedecke 建议初级工程师不要轻信 ZIRP 时代的建议，不要参与政治斗争，保持友善和尽责。他同时提醒不要恐慌 AI，也不要完全回避 AI，而应把 AI 智能体的建议当作参考，用自己的判断去理解系统，避免成为只转发 AI 输出的“肉代理”。

    Awaiting translation

  2. Boris Cherny60

    Claude Tag 在 Slack 中现已支持个人连接器，可直接访问个人有权限的 Drive 文档、Salesforce 账号或数仓表，今天在 Teams 上线、下周面向 Enterprise 开放。

    Awaiting translation

    QuotedNoah Zweben@noahzweben

    Claude Tag in Slack can now use your personal connectors! You can now securely access that Drive doc, Salesforce account, or Warehouse table that you have personal access to right where the work happens. Avail. on Teams today and Enterprise next week https://claude.com/blog/claude-tag-now-supports-personal-connectors-in-channels

9/25Fri
9/24Thu
  1. Lovable · Blog71

    Lovable ships Chats, and opens up the trajectory and inbox architecture behind its multi-agent collaboration

    Lovable launches Chats, an agent that runs at the workspace level, can hold conversations across projects and trigger builds; once changes are confirmed, it hands the task off to the project's builder agent and brings progress back into the conversation.

    Why it matters: Lovable shares the three-layer architecture behind Chats—trajectory, inbox, and activation—which you can adapt for your own multi-agent orchestration.

9/23Wed
9/22Tue
  1. Cursor Forum · Guides48

    Cursor 多包 monorepo 上下文管理架构指南

    Cursor 官方指南给出三步配置，解决 Composer 在大型 monorepo 中跨包串上下文、混淆前后端约定的问题。做法是在各子包放置轻量 .cursorrules 而非单一根文件，因为 Composer 会优先采用离当前打开文件最近的规则文件；提示时显式引用相对路径（如 @packages/api/src/...），避免全工作区模糊语义搜索，让提示词预算集中在当前包的 AST 上。

    Awaiting translation

  2. AI Coder · Telegram78

    Role-Based Model Routing in Claude Code: One Week of Practice and Hook Enforcement

    Drawing on his own Codex setup, the author built a role-based model routing system for Claude Code: the main thread acts as coordinator, explorer uses Haiku for code search only, worker uses Opus for TDD implementation, verifier uses Sonnet to run checks independently, senior uses high-tier Opus for money, data, and concurrency, and reviewer switches to a different model for semantic review.

    Why it matters: Based on a week of hands-on testing, the author shares the configuration, Hook enforcement, and cost trade-offs of multi-model division of labor in Claude Code, which you can adapt to your own multi-agent workflows.

9/20Sun
  1. 陈与小金 · AI Coding 博客66

    为什么越让 AI「不要」做什么它越做，以及提示词剪枝优化怎么做

    作者指出负向提示词会把「不要」后面的词以高权重送进模型注意力，导致模型反而生成被禁止的内容，就像让人别想粉色大象。解法是剪枝优化：把「不要写长句子」这类黑名单改成正向闭集白名单，用具体动作替代抽象禁止，并把已弃用工具的历史叙事从规则文档中彻底删除。

    Awaiting translation