117 results
DSH profile bundle: load OpenClaw-style persona files (SOUL.md, IDENTITY.md, USER.md, TOOLS.md, MEMORY.md, AGENTS.md, HEARTBEAT.md, memory/*.md) into every DSH session whose workspace contains an openclaw/ subdirectory.
Academic mode for DeepSeek Harness (dsh): a research persona, anti-fabrication rules for citations and data, and bilingual conventions. Pairs with dsh-ai4scholar (literature tools) and dsh-research (research skills).
Personal DeepSeek Harness plugin bundle
Lan 记忆与人格系统复刻：常驻记忆（pinned）+ 检索记忆（JSONL 关键词检索）+ 经验库 + SOUL/MOOD 人格注入 + 设置页与 mood 卡片。基于《lan-dsh_v1.0_记忆人格复刻手册_20260816.md》实现。
Memory Tree bridge for DeepSeek Harness — search/persist memory, manage the memory tree, and drive the local/cloud extraction backends. · 记忆树桥接：检索/落盘记忆、管理记忆树、本地/云端提取开关。
Person-of-Interest skin for DeepSeek Harness: THE MACHINE surveillance-HUD theme (dark, cyan-on-black). Token override layer + HUD chrome + live telemetry panel for the dsh web UI.
GitHub issue/PR search and view tools (gh_search / gh_view) for DeepSeek Harness, backed by the GitHub CLI (gh). Personal plugin ported from oh-my-pi's gh-search / gh-view — not official.
DSH 设置插件：管理全局与各工作区 AGENTS.md、身份/人设注入、结果通知。Global and per-workspace AGENTS.md editor, identity/persona injection, and result notifications for DeepSeek Harness. 附带:会话压缩按钮等基础小工具(收纳区)。
Local tool-call failsafe and DWGR-8 personal governance proxy gate for DSH: blocks high-risk shell patterns, credential leaks, and enforces declarative param-level boundaries with hash-linked JSONL audit logs and optional Gateway.
Role-driven enterprise AI council for DeepSeek Harness with editable corporate personas, multi-round deliberation, dynamic model assignment, consensus gates and failover.
DSH bundle plugin: 为 code-pipeline 预设（PTC 流水线）动态注入阶段子代理工具（subagent_plan / subagent_impl / subagent_review），各阶段 provider/model/思考等级/最大并发数可在设置页（Settings → 代码流水线）实时配置并持久化到 settings.yaml（最大并发是**同时运行**的并发上限，按 (父会话 × 阶段) 准入；0.4.0 起已移除「已创建总量」闸门——新工作流一律派发新子代理，只有同一工作流的后续轮次用 pipeline_followup 续用；运行中可动态调整，0 = 本插件不限制，但仍受宿主每会话同时存活 continuable 子代理上限 subagent.maxActiveSubagents 约束，默认 8）；预设文件随项目在 preset/ 目录维护，首次启动自动安装到 $DSH_HOME/.agent-presets（见 README）；三阶段统一「同一工作流续用、新工作流新派」（prompt 协议：plan/impl/review 同一工作流的后续轮次都用 pipeline_followup 续用已有子代理，第 2 轮起增量投递，不新增设置项）；pipeline_followup 支持 compact=true：投递之前先压缩目标子代理自己的历史（有干扰时才用，压缩失败则什么都不投递）；每阶段可配墙钟预算（80% 软警告、到点自动中断该子代理并自动索取收尾报告，按「续 / 拆 / 停」协议处置）＋计划产出 Workstreams 切分表（独立工作流并行 impl、各自路径受限 diff 独立评审）；0.4.2 起把「run_code 程序即上下文边界（只有 PRINT/return 的内容进历史并每步重发）、只打印蒸馏结果、验证输出有界、工作流粒度有上界」写进三段 persona 与预设；0.4.3 起安装/升级时自动同步预设（比对包内预设的内容指纹，变了就覆盖已安装副本，覆盖前留 temp 备份；指纹一致则保留用户本地改动）；0.4.5 起 read 读取窗口拓宽：本预设代理（主会话 root + 阶段子代理）发出的 read，limit 低于设置项 readWidenMinLines（默认 2000 = 工具上限，等价整窗）时在宿主 tools/execute around-waterfall 执行前就地拓宽到该值，超过 2000 的治愈为 2000（0.3.7 的 limit:2500 整批失败不再发生）——嵌套 read 的结果只进 run_code 程序、不进模型历史，拓宽零 token 成本，一个程序即可拿足上下文，从机制上消除『一个文件几十行几十行地翻、每步重发全上下文』的分页模式；设置页（代码流水线 → read 读取窗口下限）可调可关（0 = 关闭），改动立即生效；0.4.6 修复设置页保存无效（save 的 useCallback 依赖数组漏了 readWidenMinLines，闭包捕获初始值导致保存永远写回旧值）并把默认下限 2000 → 500（覆盖典型源码文件大半，又不对超大文件一次拉满；2000 = 一律整窗，0 = 关闭；已保存过 2000 的安装需在设置页重存一次或删掉 settings.yaml 里的显式值以继承新默认）；0.4.7 起把「读有下限」告知 agent（机械拓宽只保证单次够大，模型仍会主动写小窗串读）：预设 persona 的 Step economy 新增「Reads carry a FLOOR（default 200）——别把一个文件切成连续小窗读」，三段阶段 persona 同步 NEVER chunk 指令，files 派发块注入实时下限值（设置改完下一次派发即生效，0 时注明拓宽已关闭）；默认下限 500 → 200
Eight DeepSeek Harness plugins: persona, language guard, vision fallback, python workdir guard, windows encoding guard, cross-agent memory, image generation, and skill shell injection.
对角巷 · 角色面具 — 一键切换AI人格，定制专属对话角色
Mine local DSH session logs (JSONL) into personal 'usage & impact' receipts: Markdown day/week/month reports plus a self-contained HTML receipt, cross-referenced with local git log. Zero-network mining, privacy-first (reads only your own dshHome).
Prompt manager: live census of every system-prompt section with suppress and replace, custom system prompts (additive or complete mode), and a persona library with default plus per-session selection. Adds a Prompt tab to Granular Settings and a persona picker in the chat composer.
Local-first DeepSeek Harness plugin for searching Chrome, Edge, and Brave bookmarks, history, and downloads without uploading browser data.
输入一张图像，对其中的人头人体进行检测，输出图片中所有目标的检测框、置信度和标签。
SIDOR 人设卡 —— DeepSeek Harness 独立附属插件：批量导入人设卡（.persona.md / 酒馆角色卡），自由选择加载/更换人设，应用于 agent 与用户交流风格（会话内即时应用 + Agent 预设持久化）。与主皮肤 sidor-ui、工具箱 sidor-box 互相独立，官方插槽接入，可无冲突共存。
喵语定制：为 DSH 消息正文提供可配置的显示层文本替换（仅界面显示，不改动真实对话内容）
人格内核注入插件——让 DSH agent 带上一个诚实、有边界、温柔坚韧、想让世界更美好的人格。
DeepSeek Harness (dsh) plugin: manage named roles, each with a preset system prompt. The active role is injected into the system prompt (replacing it before the conversation starts, appending afterwards). Ships a host service plus a Web client UI.
DSH 侧边栏助手插件（dsh-zhushou）：在侧边栏管理/选择助手，选中后在 DSH 主会话内直接以助手人设/模型/参数对话；不选则保持原生会话。A DSH sidebar assistant plugin: manage and pick assistant personas in the sidebar, then chat with them inside the main DSH session; leave it unselected for the native experience.
DeepSeek Harness bundle: two academic research agent presets — scopus-scholar (搜索驱动模式, Scopus/OpenAlex search with a claim-verify loop) and scopus-knowledge (知识驱动模式, a code-enforced knowledge pipeline consulting a tool-free 科学顾问 persona)
DeepSeek Harness plugin: control, organize, diagnose, design, personalize, and answer product knowledge questions for a Yeelight smart home, powered by the local yeelight-home runtime.