Plugins

Windows Computer Use for DeepSeek Harness with 21 tools and verified targeting: controls are addressed through their UI Automation identity and patterns, and numbered marks are checked against the live window before input, so a stale target is refused instead of clicked. A known sequence runs in one computer_batch call, one model round trip; incremental observations and 2.0.0 compact receipts, normally no more than about 6 KiB extra, keep context small. Human handoff, approval modes, a model-visible stop brake and prebuilt native workers.

为 DeepSeek Harness 提供 macOS 与 Windows 风格界面、主题配色、壁纸和字体设置，以及可独立开关的蓝鲸桌宠。

Adds a restart button to the DeepSeek Harness desktop app — it asks before restarting while work is running, and afterwards reports how long the app was down. Entries can live in the sidebar, the conversation header, the account menu or the settings page, and each one can be turned off. Extras include checking how much sign-in data is stored (a cause of startup failures) and previewing leftover temp files, counted but never deleted. Desktop app only.

Local-first hands-free AI voice assistant plugin for DeepSeek Harness (DSH), with speech-to-text, text-to-speech, voice commands, and local speech engines.

Arknights: Endfield theme for the DeepSeek Harness Web GUI: charcoal and hazard-yellow industrial HUD, a boot splash injected ahead of the shell, a conversation backdrop, and a re-cut Windows title bar. Restyles the sidebar brand to 终末地工业 / ENDFIELD INDUSTRIES, which a URL flag reverts.

Hierarchical Claude Code-style memory: user + project scopes (project memories committed to git for the team), MEMORY.md index auto-injected at session start, context-window guards, pure files.

Lifecycle notification layer for AI coding agents — DeepSeek Harness 0.2 plugin: OS notification, in-page toast, and optional sound when a turn, background job, review, or failure needs you.

Use your logged-in web AI (DeepSeek, GLM, Kimi, Qwen, Doubao...) as model providers in DeepSeek Harness. Web models emit tool calls, DSH runs them under its native permission system, and results return to the same web session. No API keys.

Multi-threaded downloader plugin for DeepSeek Harness with bundled aria2: probes the target for Range support, then picks aria2 (4 or 8 connections by file size) or falls back to curl.

Deterministic project actions shared by people and agents: one actions.json, a right-sidebar run panel, and agent tools.

Codex-style conversation outline for DeepSeek Harness: a floating panel listing every user question in the current conversation with search, load-older and click-to-jump (scroll + highlight). Bilingual zh-CN / en.

Shares a local memory pool between DeepSeek web chat and DSH, with automatic DSM-tag capture, full-answer saving, named retrieval, and sidebar injection. The optional desktop patch for DSH 0.2.2-rc.1 adds same-window DeepSeek chat, selection-to-memory, and zoom. Chrome/Edge extension is optional and used for external browser chat.

Remote development launcher for DeepSeek Harness: provisions dsh on a remote host via SSH (or a local WSL distro) and connects from the local client, with LLM credentials proxied through a reverse tunnel so they never leave the local machine. Ships as both a standalone CLI and a dsh plugin with a session panel, /remote-explorer slash command and remote_* agent tools.

A judgment core for DeepSeek Harness: a cognition loop that gives every decision a source and attribution and drives planning to a close, hippocampus memory that condenses running experience into knowledge (journal ledger, episodic archive, low-confidence decay), judgment identity responsibilities in the architecture (consistent rubric, judgment bound to its source), and an A2A memory-management team via dsh-linghun-assembler. Requires DSH ^0.1.0-rc.7 (rc.2 supported).

Takes over the built-in web_search and web_fetch providers with Tavily, each behind its own toggle: a key pool with balance-aware scheduling that reads real credit balances from /usage, failover with hard exclusion of cooling or exhausted keys, and call history with a 14-day credit chart.

Model switching and reasoning-effort control for DeepSeek Harness: set_model and list_models agent tools let the agent autonomously change its provider, model or thinking depth (reasoning effort) mid-task with a mandatory reason, a provider whitelist and a context-window token-pressure guard, the active model is injected into the runtime context, and Plan Mode auto-transition switches to a configured planning model on entering plan mode and restores the previous execution model on exit.

Startup splash for DeepSeek Harness: an animated avatar with aurora, stardust, pointer parallax and a module-assembly entrance, plus the same image as the main-UI wallpaper; both images can be swapped from a settings page that previews the animation live.

J-Space Cognition Suite SV1 native agent preset and standalone Cordis plugin: 13 modules, persistent controller and decoupled workspace.

Registers six spec-driven + test-driven workflow skills for DeepSeek Harness: OpenSpec spec authoring fused with Superpowers TDD discipline into a Phase 0-4 pipeline with review gates. Zero runtime dependencies.

Omni-modal workstation for DSH: analyze_image over an ordered multi-card VLM failover chain, a six-tool vision toolkit (zoom, colour sampling, pixel diff, OCR, element detection, inline display) sharing the same image resolver, generate_image over OpenAI/DashScope/ComfyUI protocols, multi-card async generate_video with a /build-video-tool builder, and speak/clone_voice TTS over seven providers, all driven by one auto-saving settings page.

Reads the files that AGENTS.md references with @path imports and injects their content into model context, with byte budgets, compaction re-seeding and a six-language settings card. v0.3.x expands the imports of every instruction file the harness loaded, including a project AGENTS.md picked up mid-session (needs DSH 0.2.0+); use 0.2.x on DSH 0.1.7.

OpenCode Go subscription models as a DeepSeek Harness provider: re-resolves the live gateway catalog every few minutes, auto-adapts models the built-in table has not seen, and covers streaming, tool calls, image input and subscription usage. A maintained fork of dsh-opencode-go: a clash with the upstream package over the llm-opencode-go settings namespace makes it withdraw quietly instead of failing the whole plugin tree, and an already-claimed opencode-go route makes it serve on opencode-go-plus.

Spec-Driven Development pipeline for Odoo: 15 tools take a request from an immutable spec through architecture to module code or live configuration, then require a persisted verdict backed by evidence from a real Odoo instance, with fail-closed gates, human-approved batches in a declared environment, Odoo's own CSV/Excel importer, and a journal that reverses the data written through the plugin.

Custom modes / assistant manager: give each mode its own system prompt in the settings page — a custom prompt that is a plain file the agent loop re-reads before every model step, so an edit applies to the running session on its next step — and start it from the official standard / PTC / minimal / Cordis composition, toggling the plugin rows it mounts one by one (a custom plugin composition per mode), renaming it as you like. Several assistants coexist with their own prompts, so one machine can keep a coding assistant, a chat companion and a roleplay (RP) persona side by side — a multi-agent setup you pick from per new session. Rows left untouched stay byte-identical to the shipped ones, platform conditions included.