Desktop cockpit for DeepSeek Harness (dsh): token usage & cost tracking, budget alerts, runtime auto-update with rollback, Quick Ask hotkey, scheduled tasks, session search. Win+macOS. DeepSeek Harness 桌面驾驶舱：成本/用量监控 · 自动更新 · 定时任务

Expose DeepSeek Harness agent capabilities as an MCP server, so an external MCP client (e.g. Hermes) can drive Harness to execute coding tasks. Hermes = brain, Harness = arms.

DeepSeek Harness 的 TencentDB Agent Memory 移植：L0 对话捕获 → L1 结构化记忆提取 → L2 场景/L3 画像，自动召回注入 + 记忆/对话搜索工具；复用现有 ~/.memory-tencentdb/memory-tdai 数据；附 Web UI 设置栏。

本地优先、零普通运行时依赖的 DSH 项目记忆：有界会话冻结 Hot Memory、倒排 BM25 召回、生命周期与缓存命中优化、中英双语 GUI。 / Local-first DSH project memory with zero regular runtime dependencies: bounded session-frozen Hot Memory, inverted-index BM25 recall, lifecycle, cache-aware design, and a bilingual GUI.

DeepSeek Harness 的 soul.md 风格人设 + 长期记忆插件：设置页输入人设卡名称和内容即可，文件由插件自动管理；可按工作区指定人设、聊天框可给会话单独切人设；AI 可自行演化人设与记忆（soul_read/soul_update/memory_*）。

DSH 上下文注入审计插件：统计 AGENTS.md 指令链/技能目录/工具 schema 的 token 成本，检测重复与冲突；Web UI 圆环面板 + context_audit 工具。Context Doctor for DeepSeek Harness: audit instruction-chain / skill catalog / tool schemas token cost.

Self-evolving memory for DeepSeek Harness (DSH): earned experiences, diary/fact semantic memory, concern tracking, and an append-only audit ledger.

Unified DSH checkpoints: session + workspace + config three-state snapshots with one-shot rollback — /checkpoint and /rewind commands, a checkpoint tool, automatic interval snapshots, a Settings page timeline with pairwise diffs, and seed-replay session r

Local and remote knowledge bases for DeepSeek Harness, with scoped recall, controlled write-back, and a Web management console

Cross-session plaintext memory plugin for the DeepSeek Harness — deterministic BM25 recall, human-owned, no embeddings

DeepSeek Harness chat history and session management: search archives, restore conversations, and delete safely

One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.

DSH 自定义模型思考等级管理与偏好记忆插件：原生设计语言、全档位思考配置与无感隔离式跨会话偏好记忆。

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.

Unified capability menu for DeepSeek Harness: manage exposure level (context footprint) and execution mode of MCP tools & skills via Exposed/Progressive/Blocked tiers.

Import Claude Code sessions and skills into DeepSeek Harness, and sync DSH sessions back to Claude Code

A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.

DSH plugin: connect to MCP servers, discover tools, and register them for direct model invocation with retry logic and statistics

Delete DeepSeek Harness sessions from the UI: header danger button + sidebar session-row menu item (no conversation jump), risk-consent dialog with session name/id, stops running agents first, in-place list refresh without page reload. Works in web and the desktop client.

Reflect2Evolve memory plugin: layered L1/L2/L3 memory, reflection-weighted value backprop, cross-task policy induction, skill crystallization, and three-tier retrieval for OpenClaw, Hermes Agent, and DeepSeek Harness.

Open-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included.

DSH 声音提醒 + 对话直达插件：多对话并行时，哪个对话有回复就出声提醒，点右上角卡片直达对应对话；切到别的应用时还有系统级通知（macOS 通知中心 / Windows toast），点击直达。当前对话当/当当（crisp 档），其他对话叮/叮叮（soft 档）。

DeepSeek bills peak hours at 2x, and peak is 09-12 and 14-18 Beijing time. npx dsh-lean audit shows what your session paid and what it costs off-peak. DeepSeek 峰时按 2 倍计费，峰时正好是上班时间。

High-reliability Feishu/Lark bridge for DeepSeek Harness — QR one-click auth, multi-mode agents, card-based commands, zero-loss outbox, media in/out, session logs, reusable DSH Web GUI