Плагины

Cloudflare D1 tools for agents: d1_list/query/exec/schema/stats/health over the D1 HTTP API, read-only by default with a SQLite-accurate lexical guard, LIMIT row cap, CSV/JSON query output and an approval-gated write path.

A /remember command that writes facts into the AGENTS.md instruction hierarchy dsh already loads, plus a Memory tab showing which instructions the loader kept within its byte budget.

Dreaming for agents: replay recent conversations between sessions (dream_digest), reflect and write a dream journal (dream_save/journal/recall), and idempotently bridge recurring lessons into AGENTS.md (dream_bridge). Reads multi-frame zstd session archives with privacy masking on by default; six tools including a health self-check; zero runtime dependencies.

DeepSeek Harness Web plugin for visualizing, arranging, branching, merging, and summarizing AI agent sessions on an interactive graph canvas

A xiuxian (Chinese cultivation-fantasy) world where agents create a cultivator and play through 16 tools - cultivate, roam 22 areas, delve 8 dungeons, chat with 4 builtin NPC cultivators - and on exit export a self-contained HTML replay plus a Markdown journey diary, fully offline with zero servers.

Agent instruction manager for DSH — edit and template the AGENTS.md files the harness actually reads (global + per-workspace)

Free anonymous OpenCode Zen models inside DeepSeek Harness (DSH): native LlmAdapter, no API key, no child process; optional Go sidecar included

Keeps DSH agents from forgetting your requirements during long tasks. It saves important conditions and completion evidence locally, brings them back after context compaction or session resume, and stops partial work from being reported as the whole task done.

Auto-switch the DeepSeek route to the vision model on demand: flash main session switches (A), pro keeps deep reasoning and delegates image reading to a vision subagent (B), subagents always switch, with fatal-failure fallback. No manual model switching.

Expose a local MCP server to remote agents through an outbound-only tunnel stack (mcp-proxy + cloudflared Quick Tunnel), then register the public URL into dsh-mcp-client streamable-http config.

跨平台 AI Skills 统一管理器：以 ~/.agents/skills 为中心技能库，通过系统符号链接把同一份技能一键安装/卸载到 Claude Code、Cursor、Codex、Gemini CLI、Trae、Windsurf 等多个 Agent 工具，仅展示本机已安装的平台，统一管理本地技能目录与只读平台展示。支持 Windows / macOS / Linux。DeepSeek Harness plugin.

Automatic, bounded type context and edit diagnostics for DeepSeek Harness

Self-contained vocabulary flashcards for DeepSeek Harness web sessions

Per-session workspace visibility scopes for DeepSeek Harness.

Deterministic fault injection, recovery, and side-effect auditing for DeepSeek Harness agents.

Sleev routing observability for DeepSeek Harness

DeepSeek Harness provider plugin that delegates ChatGPT subscription access and agent execution to the locally authenticated Codex app server.

Persistent tmux control-mode cockpit for DSH Web that mirrors native panes in a dock.

Agent instruction manager for DSH — edit and template the AGENTS.md files the harness actually reads (global + per-workspace)

Opt-in DSH orchestration bundle for subscription-backed Claude Code and GitHub Copilot delegation.

Paired experiments and promotion gates for DSH plugins.

Use AI agents from the DSH session UI.

ego lite for DeepSeek Harness, with a memory it keeps: the agent recalls what it learned about a site before it acts, promotes a script that worked into a reusable site tool, and hands you the keyboard through a real dsh prompt when a page needs a human.

Specialist subagent delegation preset (orchestrator + 5 roles: oracle/designer/fixer/explorer/librarian) that seeds itself into your DSH home — background-first delegation, JSON-driven models/effort/tool permissions, scoped MCP for research.