139 results
为 DeepSeek Harness 带来分层记忆（全局 / 用户 / 项目 / GIT 分支 / 每日）与自我进化（经验沉淀 + 技能自动创建）和技能管理、待办管理、CLI 调度（kimi/codex/grok/hermes 等外部 AI 统一调度）、临时信息便签，带 WebUI 管理界面。Hermes-style long-term memory, self-evolution, skills, todos and external CLI agent dispatch for DeepSeek Harness.
超级模组注入器：运行时注入任意本地 DSH 插件包（junction 链接 + loader.create，不碰 patch/package.json/不重启），热重载全家桶 + 开发侧挂区一键转正 + 一键卸载 + 路由自愈 + 插件管理 UI（设置页：列表/卸载/拖入内化），清单持久化重启自动恢复——DSH 生态的 BepInEx 式模组注入入口
DeepSeek Harness plugin: dispatch work to DSH agents from Claude Code / Codex, as native subagents with live progress
独立 dsh 插件：会话内初始化/接入本地王国，Territory/Binding CRUD + Task 治理闭环（Worker Claim ≠ Fact）+ Execution 生命周期 + v0.8 Persistent Governed Worker（长期 Session / Territory Affinity / Capability Gate / Execution Lease / Dispatch Evidence / Reconciliation）+ 本地 GUI 通道
Morning Star harness dsh (DeepSeek Harness) cordis function plugin — in-process engine gates (status/dispatch/lease) with hard refusal channels.
dsh plugin: register locally-defined custom agents (~/.dsh/agents/*.md) as callable subagents via the use_agent tool, with continuable background dispatch and ask_agent follow-ups
DSH plugin health checker: scan plugin repos for manifest protocol / patch format / build pitfalls / hub registration, zero-dependency read-only diagnostics
DSH plugin health checker: scan plugin repos for manifest protocol / patch format / build pitfalls / hub registration, zero-dependency read-only diagnostics
AI-native web scraping and JavaScript reverse-engineering platform powered by DSH, Patchright/CDP, semantic recovery, and verifiable Solvers
DSH 插件健康检查：设置面板内的「插件检测」向导 — L0 静态检查（files 白名单/依赖声明/高危副本/依赖可解析/Windows 命令/lockfile 一致性）+ L1 配置组合检查 + L2 隔离试跑（子进程 boot 全树），发现即自动回滚（写 home patch 前弹确认），复杂问题打包预制提示词交给 agent 修复。铁律：只修改插件代码与配置层，严禁修改 harness 源码。
DSH skin plugin: built-in skins + custom image skins, pure client plugin (no source patch)
插件管家——图形化插件管理：中文名与用途说明目录 + 一键启停（写入全局 cordis.patch.yml，实时热生效）
In-session cross-agent dispatch for DeepSeek Harness: a zero-dependency skill and a host-only bundle that send self-contained tasks to 11 external agent CLIs (Codex, Claude Code, TraeCode, OpenCode, Gemini, Cursor, Kimi, Qwen, Copilot, WorkBuddy, Grok).
Hook DeepSeek Harness into your Hermes pipeline: dispatch-spec template, model-tier routing, quality gates, git single-writer rule — as an installable skill pack.
Android Logcat viewer for the dsh web GUI: auto-connects to any adb device in debug mode, live logcat stream with level/keyword filters, pause/clear/export, plus agent tools (logcat_recent). Hot-pluggable — mounted via ~/.dsh/cordis.patch.yml + a profile node_modules copy, no dsh source changes.
DeepSeek Harness 子 Agent 派发插件：按任务为子代理选模型、推理强度与工具范围，常用组合存成命名方案随时复用；内置安全检查、成本估算与节省分析、完整决策台账。
DSH diff tool: structured comparison of text/JSON/CSV/Markdown plus unified diff generation and in-memory patch validation. Zero-dependency, read-only.
Persistent global fetch proxy for DeepSeek Harness LLM requests (undici setGlobalDispatcher + EnvHttpProxyAgent), configured via the llm-proxy settings namespace
Multi-agent collaboration suite for DeepSeek Harness: a user-configured specialist roster with on-demand dispatch (team_call / roundtable), model comparison, and a multimodal vision bridge — models come from the official provider flow, no bundled adapters.
MCP 服务器管理面板：GUI 增删改 MCP 服务器配置（写入 profile cordis.patch.yml 的 mcp-client insert 行，配置 HMR 实时挂载）+ 工具浏览 + agent 面 mcp_* 管理工具。连接生命周期委托官方 @deepseek-ai/dsh-mcp-client。
Config-driven lifecycle hooks plugin for DeepSeek Harness: declare event -> command hooks in cordis.patch.yml, no plugin code required. Includes a Hooks section in the Web GUI settings (history timeline + manual tester + notify tests + hook editor + Feishu connect).
Discovery + management wrappers around the gh CLI for AI coding agents. Ships as a standard agent skill, an Agent Plugins 1.0 plugin (plugin.json + skills/), and a dsh plugin (dsh.bundle.patch registers the skill at runtime).
通用 DSH 插件库（pnpm monorepo）：模板插件、插件开发工具包、一键聚合安装包。根包同时是全家桶 bundle（dsh.bundle.patch），DSH 与插件市场可直接识别安装。
Best-of-3/5 orchestration and LLM-as-a-Verifier selection for DeepSeek Harness