Plugins

Microsoft Agent Framework (MAF) plugin for DeepSeek Harness: validate, run, and scaffold declarative agents and workflows (YAML).

Task Runner mode for DeepSeek Harness: the main agent decomposes large tasks into independent subtasks, dispatches them to subagents (default local model) in fresh short contexts, and synthesizes results; concurrency and worker/orchestrator models are configurable in the settings panel.

Jimu (积木): domain-based orchestration plugin for DeepSeek Harness — domain_plan confirmation, per-domain sub-agents with hand-off, and automatic LLM audit.

Claude Code style /init command and tool that writes a minimal CLAUDE.md and symlinks AGENTS.md to it.

dsh port of the shared handoff kit: handoff and task-id-bootstrap skills plus host-side automation — baseline state injection, per-turn snapshots with an Auto Log trail, task=<id> routing, continuation re-injection, a compaction guard with clear-required alerts, and read-only subagent handling — all writing the same .agents/state/ as the Codex, Claude, and pi editions for one-repo multi-agent handoff.

Tree-shaped Markdown knowledge base for DSH agents: kb_list/kb_read/kb_write tools, tree/node HTTP routes, and a browser panel companion.

Adds a Managed Agents settings tab and MCP tools to dispatch long-running agent tasks to Ark cloud Managed Agents.

Realtime Avatar (realtimeavatar.ai) for agents: the developer API key held by the harness credentials store, the public docs as five on-demand skills, rta_* tools over the public REST API (balance, avatars, clips, sessions, usage) with approval-gated credit spending, and a /rta command that walks a developer from no key to a live avatar call.

Answers hard questions by staging a formal debate: two adversarial subagents argue opposite sides with research, then the main agent rules on the transcript through the debate_open, debate_round, and debate_verdict tools.

Turns a Xiaohongshu, Douyin, TikTok, YouTube or X link into text: transcript with timecodes, on-screen text, a description and OCR of every image, caption and metadata. Mounts the hosted MCP server over streamable HTTP.

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.

WebUI panel for the dsh-guardian watchdog: start, stop and inspect two macOS LaunchAgents with status, log tail and explicit failure states.

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.

Settings panel for global and per-workspace AGENTS.md, with identity and persona injection, runtime-context toggle, and result notifications.

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.

Built-in Obsidian-style knowledge base for DSH: agents distill conversations, documents and web sources into a structured .wiki graph, with retrieval, graph export, note editing, incremental builds and multi-vault management.

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.