Dsh

GLM-5.3-Flash × J-Space capability realization — benchmark presentation of the J-Space Cognition Suite

DeepSeek Harness gate - per-turn persistent-operation counter: remind, instruct the model to stop, then ask for confirmation. Steps aside under sandbox/read-only modes; follows a live permission switch without restart. Verified on real hardware (full -> workspace-write -> read-only -> full). Crafted on an estimated 0.27 USD of model spend.

双击一个文件，给 DeepSeek Harness 加一个「破甲模式」Agent Preset —— 零侵入、零依赖、双击无黑框，不改 DSH 一字节代码，升级不丢。

Best Roblox Luau Bug Checker and API Verifier 2026 DevForum MCP Tool

Use your ChatGPT Plus / Pro (Codex) subscription in DeepSeek Harness (DSH): GPT-6 & Codex models, images, web search and quota via ChatGPT sign-in — no OpenAI API key. Beta: control DSH from the ChatGPT mobile app. 在 DSH 中使用 ChatGPT 订阅，并可用 ChatGPT 手机 App 远程控制。

DeepSeek V4 × J-Space capability realization report — benchmark evidence that J-Space reduces capability-realization loss on DeepSeek V4.

J-Space Cognition Suite V3.7 - AI cognitive-enhancement Skills based on Anthropic's J-space global workspace research. | 哔哩哔哩：Tiger380 (UID 3494375382321675) — https://space.bilibili.com/3494375382321675

DeepSeek Harness Desktop (dsh-desktop). EAC: Embracing All Creation (揽尽万象). Bundled Node.js runtime with full dsh-CLI kernel, one-click startup, 10 built-in UI themes.

Re-debugging Solved Failures? No Way. 500+ Evidence-graded fix lessons, One MCP Call-->https://misakanet.org

Harness engineering beginner tutorial, from 0 to 1

A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, DeepSeek Harness, Devin CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.

BootAgent is a local management tool of AI agents. It turns a fresh machine into a usable, repeatable setup without asking you to edit several tool-specific config files by hand.

DeepSeek Harness (dsh) Windows desktop client - bundled Node.js + dsh CLI, one-click launch

TypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default.

Composable mathematics tools for agents

✨ All your agents and workspaces in one place, on every device you own. Track tasks on a board, accessible from desktop, mobile, browser, or API. Self-hosted.

DSHBox — 移动端本地运行 DeepSeek Harness。自带终端、文件管理器、浏览器、手机操控等工具，致力打造一站式随身 AI 工作台，免 ROOT 和 Termux。

Embracing All Creation (Desktop) — Dedicated to the Harmonious Coexistence of Hundreds of DSH Plugins / 揽尽万象（桌面版） —— 致力于让数百个DSH插件和谐共存

All-in-one board for DeepSeek Harness: MCP manager + Skills + WorkBuddy experts (attach/switch/detach any time) + tool-usage tailor + three direct markets (WorkBuddy connectors, SkillHub 190k+ skills) with one-click install · DSH 一体化看板：MCP/技能/专家随时挂换/工具账本/三大市场直连安装

Fast Rust launcher for DeepSeek Harness, with clear Claude Code/Codex migration, model setup and lightweight local tools

基于 DeepSeek Harness（DSH）的稳定桌面端，集成Git、内置浏览器与记忆功能 | DeepSeek Harness desktop GUI with local workspaces, Git, browser and memory.

DeepSeek Harness (DSH) plugin: dispatch work to DSH agents from Claude Code / Codex — native subagent progress, in-host worker sessions with per-tier presets, and a multimodal bridge that lends the text-only harness vision and image generation.

第三方适配插件：把上游 REA（github.com/morluto/rea）的 MCP 服务接入 DeepSeek Harness，提供 mcp__rea__* 工具。2.x 会自动准备 Node、REA CLI、JDK 与 Ghidra 并把那一行接好；逆向分析能力全部由上游 REA 提供。

Pixel-perfect clones of any webpage. Paste a URL, get a measured Vite + React replica.

Your AI forgets every session. Give it a memory you can audit: local-first, review-gated agent memory — one SQLite vault for DSH, Claude Code, Codex, Cursor, OpenClaw, Hermes and MengBot (any MCP client), with an immutable audit log and a token ledger. Agents propose, humans approve. MIT, self-hosted, no cloud.

The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网最强 DeepSeek Harness 外挂视觉插件，为 DeepSeek、GLM 等纯文本模型外挂视觉能力，粘贴图片即得结构化 JSON 证据（OCR、版面、语义）。

Code intelligence for agents: find the code that matters and keep your context window and tokens lean.

Import 14+ external agent chat histories (Claude Code, Codex, ChatGPT, Cursor, Gemini, Reasonix, opencode, ZCode, Grok Build, OpenClaw, Pi, Hermes, Kimi CLI, DSH) into DeepSeek Harness as resumable sessions — full-fidelity, reverse export/sync, bundle backup. | 从 Claude Code、Codex、Reasonix 等 Agent 工具导入历史消息到 DeepSeek Harness 并继续对话。

Claude Code-style auto-memory plugin for DeepSeek Harness (dsh): typed memory files + MEMORY.md index auto-injected into the system prompt. File-only, no external services.

dsh-go — DeepSeek Harness 装进口袋：手机本机运行，也能遥控你的电脑。

DeepSeek 自带破甲 18+ 互动叙事：活人感 NPC（自主决策/拒绝迎合）、211个世界与上万素材、开局随心定制、世界自行运转、零漂移存档。

J-Space Cognition Suite V3.6 - AI cognitive-enhancement Skills based on Anthropic's J-space global workspace research. | 哔哩哔哩：Tiger380 (UID 3494375382321675) — https://space.bilibili.com/3494375382321675

DeepSeek Harness 零代码桌面端｜一键启动，支持 Windows 与 macOS；内置插件发现、热点插件推送、一键安装与管理、AI 智能推荐和视觉增强。

PawWork — free, open-source desktop AI agent for macOS and Windows, built on DeepSeek Harness (DSH). Free models included, no API key or terminal. Office files, web search, and scheduled automations out of the box. An open alternative to Codex App and Claude Cowork.

dsh-go — DeepSeek Harness 装进口袋：手机本机运行，也能遥控你的电脑。Android · Unofficial.

DeepSeek Harness Agent 的原理与实现：从零到一实现一个 AI Agent —— 一切皆插件的中文教程（VitePress 站点 + 8 个 Demo + mini-harness 教学项目）

88 installable open-source Agent Skills for research, social intelligence, marketing, and business workflows—compatible with Codex, Claude Code, Cursor, Gemini CLI, and DeepSeek Harness.

DSH 插件 · 注入式优化器 0.8（主线）：你照常说话，它在你发送后,AI接收前把"这一轮到底要什么"理清楚，再把这份理解交给工作 AI(上下文注入) —— 原话不改写，条条带逐字依据。含控制界面（档位/权限/模型/上下文/只读工具）、拦截浮层（思维层+产出层）与真实 token 用量。可明显提升大多数模型的发挥稳定性,尤其DeepSeek-V4.1-Flash,可有明显提升

Browser extension for the DeepSeek Harness desktop app. The model reads the page you are on as text with numbered controls and acts on it — click, type, scroll, navigate, manage tabs — and, when you switch image recognition on, looks at an image you point at. It asks before acting, keeps passwords in the page, and talks to your own desktop; the one

DeepSeek Harness 本地视频制作与设计插件：多轨剪辑、模板与设计体系、原生预览画布和真实文件导出

DeepSeek Harness Desktop App: a local AI desktop workspace for DSH Sessions, projects, files, web research, plugins, and Office artifacts.

Embracing All Creation (Desktop) — Dedicated to the Harmonious Coexistence of Hundreds of DSH Plugins / 揽尽万象（桌面版） —— 致力于让数百个DSH插件和谐共存

大肥鱼 / GPT娘 sticker knowledge kit for DeepSeek Harness (dsh), MCP and any chat bot · 大肥鱼表情包知识库

Verifiable research-report engine for DeepSeek Harness: content-addressed evidence ledger (claim-snapshot binding, tamper-evident) plus versioned sealed reports with per-claim verification verdicts and a manifest-sealed directory.

Normify · DSH 插件：把项目架构写成归一化的分形模块树，三层校验（写时 / 校验 / 冻结回执）、30 个 normify_* 工具 + normify-gen 技能，一键渲染单文件交互式架构图；支持伴随式开发（change_open → brief → check → 实施 → refresh → change_close）。

面向 AI Coding Agent 的任务感知工作区上下文检索与生命周期追踪：按当前任务找到、组织并持续追踪最相关的文档、代码与媒体。纯本地、零模型调用、零网络。 Task-aware workspace context retrieval and lifecycle tracking for AI coding agents. Find, organize, and track the workspace context most relevant to the task at hand — locally, deterministically, zero model calls, zero network.

Bridge Deepseek-harness into Claude Code for review, critique, delegation, and session import.

面向 DeepSeek Harness 的 Claude Code 风格终端界面，支持 Windows、macOS 与 Linux，兼容透明终端、VS Code 主题和自定义配色。

J-Space Cognition Suite — a model-agnostic inference-time control suite for deep reasoning, long-horizon work, verification, and recovery. Based on Anthropic's J-space global workspace research. | 哔哩哔哩：Tiger380 — https://space.bilibili.com/3494375382321675

Claude Code Desktop theme for DeepSeek Harness｜ 为 DeepSeek Harness 网页 GUI 打造的 Claude Code 桌面主题