Self-Improving：让 Agent 从纠错与复盘里自动沉淀记忆
介绍 SkillHub 社区 Skill Self-Improving + Proactive Agent（@user_814dbe54/self-improving，v1.2.16）：在用户纠正、工具失败或自我复盘时，将偏好与教训写入 ~/self-improving/ 的 HOT/WARM/COLD 分层记忆，任务前按需加载，减少重复踩坑。文章基于官方页面与 SKILL.md 说明安装命令、目录初始化、学习信号、查询口令与安全边界，并区分 Cursor、Claude Code、Codex 的 skills 路径。
Read More记忆系统框架：为 AI Agent 搭一套可落地的分层记忆
记忆系统框架是 SkillHub 社区 Skill @user_f076293a/memory-framework（v1.0.0，ai-agent，无需 API Key）。基于 OpenClaw 改良，提供 L1/L2/L3 分层记忆、WAL 决策记录、Working Buffer、learnings 复盘与每日复盘模板，适合个人助手与团队协作。文章说明定位与核心能力，并给出 skillhub CLI 安装命令及 Cursor、Claude Code、Codex 的 skills 目录差异，典型流程为安装后按 SKILL.md 初始化分层记忆与复盘。
Read Moredsh-layered-memory: DeepSeek Harness L0-L3 Layered Distillation Memory Plugin
`dsh-layered-memory` is a memory plugin designed for DeepSeek Harness, aimed at addressing issues such as context loss and repetitive questioning in long conversations and cross-session interactions. It automatically executes background processes including L0 raw conversation capture, L1 atomic memory extraction, L2 scene block integration, and L3 core profile distillation to transform conversational information into reusable memory assets. Before model execution, the plugin automatically recalls relevant memories based on length and time budgets, injecting them into the context to avoid slowing down the conversation. The plugin offers three proactive query tools, such as `memory_search`, supports four session-level memory tiers—daily, work, smart, and closed—and features a "write-only, no-read" toggle, same-session deduplication, automatic context compression resets, and time-based weighted recall functionality. The LLM token costs incurred during the distillation process are recorded.
Read More