Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.

The self-improving context engine for coding agents.

DSH Web 输入体验增强插件：可配置发送/换行键位 + 自定义输入框右键菜单 + 面板尺寸记忆 + 快捷指令（分类 / 跨分类移动 / 关·每次·仅首次三种插入模式 / 存 ~/.dsh/quick-prompts.json）+ 提示词优化（0.11.1 起工具行有独立「优化」按钮、带秒表与斜杠命令保护、写回前比对草稿） + OpenCode 会话请求头 + Windows 默认终端切换（把模型的 PowerShell 工具换成 Git Bash）+ 官方持久终端六件套（terminal_open/r

DeepSeek Harness companion for ClineBot / ClinePass: dynamic subscription models sync, quota exhaustion warnings, session metrics, dedicated settings page, live usage limits, and /cline slash-command.

Quieter sessions for Claude Code: less narration, shorter tool output and concise answers focused on the result.

Open-source deep research for AI agents: 40 channels, 10+ Chinese sources.

Build multi-model chatbots and agents from intent, with Claude Code and Codex.

Cross-platform native desktop control tools for DeepSeek Harness (Windows first): screen_shot, screen_read (accessibility tree + pixel description for text-only models), click/type/scroll/key, and app_list/app_launch — every mutating action gated by appro

OneBot v11 hub for DeepSeek Harness: connects to an upstream OneBot v11 implementation (forward WebSocket client) and serves/dials downstream bot implementations with the same protocol, relaying events and actions verbatim so DSH can observe every message

A rail of your Claude Code session's prompts: hover to read, click to jump (function hooks / Mods)

Hash-anchored read/edit/undo_last_edit tools for DeepSeek Harness (dsh). Every line gets a unique 3-char hash (A-Za-z0-9) that stays stable across edits; stale or ambiguous anchors are rejected, never fuzzy-matched. Undo persists across restarts.

DSH 环境自检：让读者看到自己电脑装了什么 —— 系统/CLI/DSH 插件/秘钥是否存在

A real PowerPoint, not HTML. Editable .pptx decks for AI agents, rendered on your own machine.

Open-source quantum Agent workspace with a desktop client, Web UI, messaging, Qiskit/MCP tools, and scientific validation

Follow the tangent. Keep the thread. Annotate, explore on the side, and bring answers back to DeepSeek Harness. / 思路可以分岔，主线始终向前。划选注释、侧边追问，再把结论带回正在推进的任务。

Production-ready prompt library for Claude coding agents. APEI methodology, ~35 specialist prompts, current Claude Code coverage, plus a /find-prompt skill that routes any task to the right prompt.

DeepSeek CLI

把外部 Agent CLI、持久终端、工作区调试和远程访问，装进 DSH 原生界面。

Multi-engine web search and evidence synthesis for AI coding agents. Unified MCP server, Pi extension, and DeepSeek Harness bundle — free search, X/Twitter, parallel research, and TUI setup.

Model router for DeepSeek Harness: keep a pool of models and every step is routed to one of them with its reasoning effort set — a click-only composer panel, three authorization scopes (a manual pick only counts in the scope that owns it, and effort scope

Your coding agents remember what you decided — and what you changed. Plain-Markdown memory in Obsidian, shared by Claude Code, Codex and Cursor over MCP. Every answer cites its page; when the vault does not know, it says so. Imports your past sessions on install.

Turn your local Claude Code / Codex CLI history into a shareable, anonymized AI-Native developer profile + viral SVG poster. A skill, not a script — 100% local & read-only.

Login gate for DeepSeek Harness (dsh) web instances: password or shared-token sign-in, optional TOTP two-factor, session cookies, rate limiting, self-service password change and a user-management CLI

Visual conversation map for DeepSeek Harness — sessions as cards on a whiteboard: drag to arrange, double-click to chat, draw an edge to fork with injected context. ADHD-friendly spatial memory. · DSH 可视化对话地图