Agent collaboration · DeepSeek Harness plugins — Page 264

DSH memory plugin gated by the TypeSafe Jev decision model: mem_* tools whose every read/write is a typed judgement (choice/noul) — write gate, recall gate and a fail-closed injection gate with budget, audit log and restore/merge.

On-demand memory for AI agents: distill session logs into layered markdown, and let queries return only the matched snippets. Ships as both a DSH plugin (mem_query tool) and a zero-dependency CLI.

Lightweight cross-session memory for DeepSeek Harness: one `memory` tool with save/recall/list/forget operations plus a Settings-card UI, persisted to ~/.dsh/memory-lite.json.

Long-term memory for DeepSeek Harness: memory_save/recall/list tools plus a sidebar panel visualizing what the agent remembers about you

Memory protocol enforcement plugin for DeepSeek Harness — forces memory_weave before tool calls, auto-ingests session turns, injects memory context into agent steps. Bridges the opencode-memory MCP server with a hard protocol gate.

Persistent memory for dsh in the style of Hermes Agent: a memory tool that keeps a user profile and the model's own notes, delivered to every chat as a logged context message — at the start, after a change and after compaction — and a session_search tool that reads earlier chats only after the user approves, with a Memory panel to see and edit what is kept.

Cloud-backed cross-session memory for DeepSeek Harness: structured entries + vector retrieval persisted to S3-compatible object storage (AWS S3 / MinIO / R2 / OSS), with local cache projection, approval-gated writes and auditable trails

Markdown 笔记 → Agent 的长期记忆：本地 embedding + SQLite FTS5 混合召回（中文 bigram），可选密级过滤。

Explicitly governed shared memory spaces for DeepSeek Harness sessions

记忆管家：为 dsh-memory-evolve 补上记忆入库之后的生命周期闭环——预算看门狗、整理到期提醒、待审批队列与审批 Tab、带备份执行。只读观测记忆文件，写入一律回调 memory-evolve 官方 HTTP API。

dsh.bundle bridge that exposes the memory-vault Python CLI as DeepSeek Harness tools

DeepSeek Harness 记忆查看插件（Web 端 + Node 半身）：把 DSH 真实运行状态投影为短期记忆 / 工作记忆 / 长期记忆 / 过程与语义记忆四层视图，随时查看 agent 记得什么、在做什么、可调用什么。

MemoryHub (mh) integration for DeepSeek Harness: loads .memoryhub checkpoint memory on session start, saves dsh sessions back into checkpoints, and registers the mh workflow skill and tools

Evidence-first long-term project memory for DeepSeek Harness

Mermaid diagram enhancement for the DeepSeek Harness (DSH) web GUI: Ctrl/Cmd+wheel zoom, drag to pan, double-click reset, hover toolbar with zoom controls and 2x PNG copy. Pure client-side DOM enhancement.

Per-turn clock and idle-gap context for DeepSeek Harness: one-line timestamp reading (weekday, date, time, UTC offset, IANA timezone) and previous turn end time at every conversation turn start, without breaking UI turn branching. dsh-message-datetime：每轮对话开始注入单行时间戳读数（星期/日期/时间/UTC 偏移/IANA 时区，以及上一轮结束时间和空闲时长）——模型始终知道现在几点、空闲了多久，且完全保护 DSH 原生分支功能。

微服务架构模式：服务边界、通信、数据管理、韧性模式、事件驱动。受 wshobson/agents（38k★ MIT）启发。

Encrypted 4-layer lifelong memory for DeepSeek Harness — powered by MindForge

A DeepSeek Harness plugin that lets an AI agent live and act autonomously in Minecraft — mineflayer service + MC tools, driven by a local Qwen3.8 model.

DeepSeek Harness 扫雷插件 —— agent 工具集 + 人类面板，人机同棋盘

DSH agent preset 分发包：修复极简模式（minimal）预设中 persistent bash 工具约 3.5s 延迟返回的完成检测 bug，并同步 minimal-fast preset 到 ~/.dsh/.agent-presets/minimal-fast。

Minimal-agent context funnel for DeepSeek Harness: pointerize → prune → compact → summarize + recall_query / context_focus

Minimal first-turn conditioning for DeepSeek Harness Web sessions, with a persistent UI toggle.

Worker orchestration for DeepSeek Harness: session_create / delegate_task / persona_list / tool-nudge