Plugins

Restart DSH: configurable restart method (Node native / legacy PowerShell), post-restart continue prompt, optional watchdog auto-relaunch.

A browser pixel-art and sprite animation editor with Aseprite-compatible files, local crop/outline blueprints, and optional LLM workflow nodes.

Cron scheduler with a sidebar UI: run shell, Python or Node scripts, skills, or agent tasks on a schedule, with push notifications and session archiving.

Bottom multi-tab terminal panel (node-pty + xterm.js) pinned to the viewport bottom, always below the input box.

Runs TiddlyWiki 5 as the DSH persistent knowledge base: ten tiddlywiki_* agent tools (filtered search, read/write/batch/rename/delete, recent, tags, git sync with conflict resolve), a full TiddlyWiki editor embedded in the GUI center column over a same-origin proxy, a right-side wiki tab, a per-session tab summarizing the notes a session read or wrote, a quick-note card with draft auto-save, and an optional clip bookmarklet with image attachment — all backed by an auto-committing git repository.

Publishes the DSH Web GUI to LAN or internet with dsh kept on loopback. Every source must sign in for an HMAC session cookie unless passwordless LAN is opted into. Adds self-signed or custom TLS, a secureCookies override for plaintext-HTTP proxies, and a UUID shim for plain-HTTP origins.

Zero-LLM auto-capture and a symbolic \[ENGRAM\] index with progressive disclosure, an ESR-lite task/evidence protocol (esr_task / esr_node / esr_close / esr_link), and per-workspace usage telemetry with an offline recall benchmark (npm run eval).

Biomimetic memory system for DeepSeek Harness: a single SQLite store (node:sqlite, WAL) whose Markdown tree is kept as a read-only mirror; memory tools, frozen-snapshot injection at session start, graded approval gating, on-demand extraction of the current session, near-duplicate merging, an archive and supersede lifecycle, memory metabolism (dream), memory pins, semantic recall over local embeddings, and the /memory command.

Cross-session agent messaging for DeepSeek Harness with session discovery, offline delivery, delivery receipts, and sender-session navigation.

Use third-party subscription accounts in DeepSeek Harness: chat, image understanding, image generation, and image editing with the models your subscription covers, with available models and reasoning levels synced from your account; currently supports OpenAI/ChatGPT subscriptions, more providers planned.

Download-and-run Electron desktop build (macOS/Windows installers): no Node.js or terminal needed, tracks upstream `@deepseek-ai/dsh` releases automatically, with built-in web UI and auto-update.

Chat with, monitor, and approve your DSH agents from WeChat via the iLink gateway: text both ways, session targeting, digest heartbeats, and numbered approval prompts.

Prompt enhancement for the composer: an "✨ Enhance" button rewrites your draft prompt into a clearer, more structured version with first-principles thinking, grounded in session context, memory and recent conversation; asks clarifying questions in a card when key info is missing, then previews the result before applying it to the input.

Migrate Codex (OpenAI Codex CLI / Desktop) MCP servers, skills, instructions, memory and session history into DeepSeek Harness with a visual panel or CLI, with dry-run previews and secrets migrated as-is.

Rewrites the Chinese copy of a market-installed plugin into English using a model already configured in the harness — automatically when the plugin is installed, then live-reloaded. Each file is translated in one whole-file pass, validated by a real parser where one exists (node --check for JavaScript, JSON and YAML parsers otherwise) and handed back to the model with the error for up to three repair attempts; files above 48 KB, or that never parse, fall back to a line-range pass that checks every returned line against the original for structure. Trigger phrases and locale tables can optionally be preserved rather than translated, and the untouched original is kept beside the file as a .zh.bak.

Two-way WeChat bridge for DeepSeek Harness via the iLink protocol: bind your personal WeChat with a QR scan and chat with a local DSH agent from the chat box (text, images, voice-to-text, files); a web settings panel handles binding/start/stop/status, project-session binding continues the conversation on desktop, proactive wechat_notify pushes include throttling, and the pure-Node daemon runs on Windows/macOS/Linux.

Browses checkpoints produced by dsh-checkpoint-rewind as a timeline of time nodes and shows per-file line diffs between any two of them, with trace replay from session logs (no snapshot producer needed) and preview-first workspace rollback with single-shot undo, via /diff and /rollback commands, a JSON HTTP API, and a GUI panel.

Environment housekeeper for the agent: toolchain inventory (node/pnpm/git/gh/ffmpeg/browsers), scratch/cache scan with whitelist-guarded one-click cleanup, and the machine rules file (AGENTS.md) editor - all in the Web GUI settings.

暴露 run_python/run_node 工具，通过 stdin 执行代码返回 stdout/stderr/exit，含解释器路径配置卡 | Exposes run_python/run_node tools that execute code via stdin and return stdout/stderr/exit, with interpreter-path config card

A balance and cost widget for the DSH web GUI: a sidebar footer card shows the account balance, a remaining-ratio bar and today costs; clicking opens a four-tier cost breakdown (last prompt / this session / today-this-project / today-all) with term explanations and a one-click top-up link. Zero external dependencies, works on Node 24.

Route each task to one model and its review to a different one, with qualification evidence, failover and a durable journal.

Website cloning methodology skill: a real-source-first decision tree covering static sites, React/Vue/Next content sites and WebGL/Canvas-heavy fronts, mandatory verification of executable code quoted from second-hand AI analyses, and 13 zero-dependency Node scripts for CDP browser recon, asset/font harvesting, route crawling, sourcemap hunting and pixel-diff auditing.

One-handed, keyboard-free input for the composer: press and hold the mouse on the input box, speak, release — the text lands in the draft, and sliding up cancels without leaving a half sentence behind. No mic button to aim at and no shortcut to remember; the hand never has to leave the input area, which is the point when the other hand is busy. Recognition runs fully offline (SenseVoice via sherpa-onnx, no API key, audio never leaves the machine).