dsh-wechat-companion
AI陪伴微信机器人 DSH 插件:iLink 官方通道消息收发、人设灵魂、主动生活、朋友圈工坊、Web后台面板
379 results
AI陪伴微信机器人 DSH 插件:iLink 官方通道消息收发、人设灵魂、主动生活、朋友圈工坊、Web后台面板
给 DSH 助手赋予人格、灵魂与长期记忆:用 Markdown 定义伙伴的身份、性格、准则与记忆,自动写日记、自动更新记忆。Give your DSH assistant a soul, personality, and long-term memory.
器灵 · 跑在你自己电脑上的记忆与人格助手插件:三层记忆、从历史里长出来的人格档案、定型锁与自由生长
Persistent cross-session local memory for DSH with Markdown SSOT and self-healing SQLite FTS mirror
OpenKapsel workspace bridge for the DeepSeek Harness: operate a remote OpenKapsel workspace (files, shell, context, memory, sharing, preview) through skill-driven tool calls using only its workspace URL and control token.
DSH plugin: unified MCP, Skills, AGENTS.md presets, archived-session and scene-memory manager — Settings UI + HTTP API + model-facing skill_mcp_manager_* / skill_manager_* / rule_manager_* tools. Install with one command: dsh plugin --profile web add dsh-plugin-tool-management@latest
CWL — Context Window Lifecycle for DeepSeek Harness: structured context eviction (arXiv:2606.11213). Graduated, deterministic, zero-LLM eviction of exploration/action episodes when context pressure exceeds budget — no summarization lossiness, no hallucination, user messages never evicted.
dsh-plugin: quality-first topic memory for dsh — a topic keeps the starting question, conclusion, impact and dependencies, not the process; local-first git-traced OKF bundle, budgeted LLM-free injection
Auditable, verifier-gated self-evolution for DeepSeek Harness.
给 DeepSeek Harness 的会话加一层「文件夹」归类:按 cwd 自动归档、手动移动到任意文件夹,文件夹路径即项目记忆作用域。 Adds a folder layer to DSH sessions: auto-file by cwd, move sessions between folders, folder path = project-memory scope.
dsh-tiered-memory
项目记忆(Project Memory):本地优先的项目记忆插件。每个项目一份 .dsh-memory.json(按 cwd 隔离),提供 memory_read/recall/write/update/delete 五工具、/memory 命令、设置页记忆管理 UI(编辑/删除/拖动排序/一键保存排序/状态过滤/搜索/多项目切换),全部遵循'随核心快速适配'(适配器+探测-退化-上报)与'万物皆插件'(可独立挂载/停用)。【单线 0.1.3】2026-09-11 起取消双线:只面向 DSH 最新核心(0.1.5-rc.1 及更新,桌面端 2.0.7+/2.0.9),不再为旧核做适配;含读取保序修复与「保存排序」二次确认/回读校验。同属 0.1.x 系列——**只有出现较大优化或新功能时才升 0.2.0**(本版暂不发布)。
System-audio driven UI visualizer for DeepSeek Harness: a draggable 48-band spectrum chip plus a frame-wide bass glow (memory-only FFT).
Persistent memory system plugin for DeepSeek Harness: atomic facts, recall/remember/consolidate engines, soul.md & user.md, and a browser settings section.
让本地 Obsidian 知识库成为 DeepSeek Harness agent 的长期记忆与工作台(索引 + 检索工具 + 会话记忆注入 + 捕获 + GUI 浮卡)
DSH 指令记忆:在设置界面中维护可增删改的长期指令,并自动注入此后每一轮对话的系统提示词。
组装式上下文(Assembled Context): a context tree over the dsh session surface with per-node assemble modes (full / key / off), agent-authored presets, and a browser panel that decides what the model actually sees.
A refutation ledger for coding agents: remember what did not work, and expire it automatically when the code it depended on changes.
Persistent cross-session memory plugin for DeepSeek Harness: workspace-scoped durable facts with model-facing memory_write/list/search/forget tools and bounded prompt injection
MemoryDirector plugin for DeepSeek Harness: LLM-driven remember/forget across turns (the official harness has no memory concept)
Action-State Memory Engine: typed time-series memory (states + actions) with trend, anomaly, and causal analysis for DeepSeek Harness
AgentFrame compaction backend for DeepSeek Harness: semantic + physical KV compression (28.4x) replacing LLM summarization
DSH-Plugin: minimal infrastructure entry — infra_status / infra_bootstrap tools that probe the mounted infra stack (memory, observability, search, skills) and report readiness.
Cross-session project memory for DeepSeek Harness: seven-layer SQLite memory, first-turn snapshot injection, per-message keyword hits, memory_remember/search/project tools, automatic reflection with reflection-fold UI, and idle-triggered dream consolidati