Plugins

LoopX, a provider-neutral, local-first state kernel and control plane for long-horizon agents: keeps Goal, Todo, gate, evidence, quota, recovery, and handoff state above DeepSeek Harness, while the plugin bootstraps the CLI and skills, admits bounded same-session continuation, and adds a loopback GoalBar for the exact bound loop.

Config-only bundle that mounts Ouroboros through the DSH MCP client, exposing 36 interview, Seed, execution, evaluation, and evolution workflow tools in DSH.

Answers a question with a one-page visual HTML explainer: the model writes a short Markdown draft and the bundled `am` CLI builds the page, with flow, sequence, tree, timeline and ER diagrams, tables and callouts.

Task board for the dsh web GUI: a sidebar multi-column kanban whose cards run in real DSH agent sessions and can also be scheduled with cron expressions, executed host-side even with the browser closed.

DeepSeek Harness plugin: the claude-slides skill from baoyu-design. The agent writes editable slide decks as files and opens them in a local slide editor.

LoopX, a provider-neutral, local-first state kernel and control plane for long-horizon agents: keeps Goal, Todo, gate, evidence, quota, recovery, and handoff state above DeepSeek Harness, while the plugin bootstraps the CLI and skills, admits bounded same-session continuation, and adds a loopback GoalBar for the exact bound loop.

Browse and search a SkillHub registry and manage local skill installation, updates, and removal inside DeepSeek Harness. Targets DSH 0.2.0-rc.2 and 0.2.1-rc.2; not yet compatible with 0.2.1-rc.3.

Full sidebar workbench with file rendering and editing, terminal, Git, and subagents; third-party plugins can register new tabs.

Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).

DS Bot: a team of long-lived Bots for DeepSeek Harness, with Main Bots, Bot-to-Bot messages and group chats

iPolloWork HyperFrames Video Studio and 27 editable video templates as a native DeepSeek Harness conversation view.

Connects DeepSeek Harness to ReMe's local-first, self-evolving personal knowledge base: automatically captures completed main-agent conversations as user-owned Markdown memory, searches conversations and source material through reme_search with BM25, optional embeddings, and wikilink expansion, and schedules daily memory consolidation.

Swaps the filesystem and bash providers for a mirage virtual workspace: file tools and shell commands run over mounted resources (RAM, S3, Redis, Slack, Gmail, Notion, Postgres) instead of the host disk, with per-mount read/write/exec modes, per-command sandbox routing (monty, pyodide, quickjs in process; docker, e2b, daytona remote), and installed CLIs (git, gh, slack, linear, ntn, gws, or one you register) as head words in the virtual terminal.

Sidebar: file rendering/terminal/Git/subagents/custom APIs.

Connect IM bots to DeepSeek Harness via QR codes or bot credentials (9 channels: Feishu, WeChat, DingTalk, WeCom, QQ, Slack, Telegram, Discord, and WhatsApp).

Connects DeepSeek Harness to ReMe's local-first, self-evolving personal knowledge base: automatically captures completed main-agent conversations as user-owned Markdown memory, searches conversations and source material through reme_search with BM25, optional embeddings, and wikilink expansion, and schedules daily memory consolidation.

AgentTeams multi-agent teams.

Shared Markdown memory for DSH and other coding agents, with automatic capture, pre-step context injection, searchable recall, and memory-to-skill self-evolution through a review panel.

Lets a DSH agent drive a local Blender over a direct TCP channel with 15 tools: viewport frames, custom-angle renders, Python execution, headless and job offload, transaction rollback, and a planning layer of 228 ops across 34 families.

给 AI Agent 的中文互联网研究 Skill：检索 8 大平台最近 30 天的讨论，追踪跨平台热点，生成附原始来源的报告，并提供每日全网热榜。支持 Claude Code、Codex、OpenClaw。

Pre-execution guard that blocks destructive Git and filesystem commands and access to secrets such as SSH keys and .env files before a tool call runs.

An agent-powered tavern for DeepSeek Harness with SillyTavern compatibility, character card imports, support for multiple models, and mobile play. Install the tavern from Settings → Tavern Launcher on desktop. A launcher derived from 2NF/dsh-profile-bridge (MIT): it downloads the tavern into a separate DSH profile and switches profiles on restart. Install this launcher or the upstream plugin, not both — they claim the same /profile-bridge channel.

Provides six code quality skills for code review, architecture audits, technical debt, test quality, health dashboards, and remediation.

Reads the session files forty-two other coding agents on this machine already wrote (Claude Code, Codex, Cursor, VS Code Copilot Chat, opencode, OpenClaw, Hermes, Kimi, Cline, Zed and more), including sessions from before it was installed: six tools (deja_recall, deja_session, deja_blame, deja_fix, deja_how, deja_remember), a /deja command, and optional automatic recall added to the runtime context. Local BM25 index, no LLM, no embeddings, no network (dsh plugin --profile web add dsh-deja).