Plugins

Installs the browser4-cli runtime and registers the Browser4 skills (browser4-cli, browser4-experience, browser4-plugin, scent-miner) into the DSH skill registry, providing an AI-native browser engine for autonomous agents, intelligent extraction, and large-scale web automation.

AI-assisted Minecraft for DeepSeek Harness: drive an autonomous Mineflayer agent (survival, mining, chat, live map) with vision/control tools, plus a built-in launcher (Microsoft sign-in, version download, game launch).

Plugin marketplace in Settings that targets any local profile, not just the running one: install, update and remove across web, headless and other profiles, with install-script warnings, an installed view that also covers non-catalog profile dependencies, and an automatic DSH restart when the current profile changes.

Agent-team orchestration sidecar for DSH: teams with a configurable member cap, real sub-agent members with per-member model routing, task DAGs that dispatch automatically when their dependencies finish, a broker that enforces fs/exec/net/env permissions, and a live web panel over SSE.

Vision-first Mac computer use, for when the accessibility tree is unavailable. Ships 11 desktop_* tools - window list, screenshots, OCR text targeting, numbered elements, coordinate clicks, typing, scrolling, drag - plus a Codex-style cursor overlay with spring animation. Clicks are delivered to the target process, so the real pointer never moves and nothing steals focus. In DSH it shows up as Mac Desktop Control with a settings page that checks the engine and the Screen Recording / Accessibility permissions, with a button that opens the matching System Settings pane. Works out of the box: the tarball bundles the dsh-cu engine and the overlay as prebuilt universal binaries (Apple silicon + Intel, macOS 11+, ad-hoc signed), compiled from the repo's Swift sources by the release workflow - no clone, no Xcode, no install.sh. The only setup is granting DeepSeek Harness Screen Recording and Accessibility once. macOS only; on Windows and Linux the plugin loads without registering the desktop tools.

Codex-style context window auto-management for DeepSeek Harness: a lossless rollover engine with zero summarization model calls, task-oriented handoff anchors, working notes that survive compaction, verbatim recall of archived windows, and a stale-notes gate that downgrades to an explicit warning instead of vouching for outdated notes. One-click composer button plus /smart-compact command, three-band automatic rollover, mandatory anchor sanitization; works out of the box with zero configuration.

One fixed button inside the DSH window that restarts DSH and reopens it automatically, with no console window; right-click it for a built-in self check that writes a single diagnostic report.

Model-autonomous context compaction for DeepSeek Harness: a mind_map tool surveys the agent context surface (stable seq ids, roles, token weights, clear-boundary markers, the clear-mind playbook), a clear_mind tool replaces a chosen conversation-history span with a model-written checkpoint through the native compaction transaction, call and result pairs self-collapse into one-line tombstones, and a proactive reminder nudges the model when the context grows long or a turn runs too many steps.

Same-origin in mechanism with the two loudest lines in context compression. The code-skeleton gate follows the skeletonization approach of Headroom (Apache-2.0), whose published headline is 20% fewer tokens for coding agents and 60–95% fewer tokens for JSON, same answers. The estimator channel follows TokenPilot (arXiv:2606.17016), which reports up to 60% lower cost for long-session agents. Both figures are theirs, quoted as-is; this plugin ships no benchmark of its own and claims no reduction of its own. What it adds for DeepSeek Harness: choose a compression profile, set the Auto Compact trigger level and toggle code-skeleton compression from one settings section, with exact DeepSeek V4 tokenizer measurement, same-revision count verification, and fail-open behaviour that keeps the original tool results on unsupported models. Within a turn it supports skeletonized information compression with a low original-text retrieval rate; at the tail of a turn it supports a turn-tail intent summary implemented purely by content substitution; context content stays safe, and the whole process runs inside the official JSONL compression.

Portable agent knowledge base in plain OKF v0.2 Markdown: 13 wiki_* read/write tools, progressive disclosure, backlinks, gated writes via AGENTS.md rules, auto index/log maintenance, linting, and named multi-bundle switching (session-level or global).

Smart session titles for DSH: after each conversation turn an independent auxiliary LLM call summarizes the full user+assistant transcript into a title that follows the session's real topic instead of echoing the first message; the first message is titled instantly, failed built-in titles auto-retry on later turns, manual renames are never overwritten, and subagent/fork sessions are skipped.

Auto-resume for interrupted agent sessions: an ordered rule table routes by failure type (rate limit, quota, auth, context overflow, crashed orphan) to automatic backoff retry, model switch, resume after context compaction, or a stop-loss notification, with a visual rule editor and a full activity log.

Switch the language of the agent's thinking/reasoning process (chain-of-thought): 简体中文, English, Русский, Français, Deutsch, Español, 日本語, 한국어 and more, or auto-follow the system locale. Adds a Settings → General row, a system-prompt instruction (per-prompt assembly, applies to new sessions), and the /thinking-language command.

Renders Wallpaper Engine scene wallpapers in real time in the browser (three.js player plus a Rust/WASM CPU particle simulation) and plays video and web wallpapers, falling back to the preview image, with no Wallpaper Engine runtime required. Scans the local Steam workshop library (431960) by auto-detection or a manual path, and offers a settings panel for wallpaper selection, library and engine directories, glow, pause and quality.

AI Company Framework: turn one sentence into a multi-agent company — 15 flat Skills (boss/pipeline/role-template/11 roles/generic customer-memory), 7 workflow templates, AgentTeams runtime + activity panel, employee sidebar with per-session isolation, Feishu bot bridge (boss and per-employee bots, group routing, autonomous push, human decision gate, external-contact guide), per-customer SQLite memory with three-layer memory (cross-group merge), /company mode switch; no RAG.

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).

Registers the DeepSeek Harness web server (dsh web) as an auto-start, self-healing background service — LaunchAgent / systemd / cron plus a 30s health-check watchdog — with seven dsh_daemon_* tools (install/uninstall/reinstall/status/start/stop/update).

Mobile remote-control suite: bundle plugin with native sidebar entry and admin drawer, self-healing bearer-token gateway over LAN/Tailscale, Android app (sessions/approvals/questions/goals), /fs/* file transfer (Range resume, 2GB upload), latency-based multi-server auto-switch, offline chat cache.

Automatically generates and displays images in the DSH chat via API channels or local CLIs (mmx / codex / agy), and can also recognize images using the corresponding CLI.

External vision plugin for DeepSeek Harness: whale-button config panel, image recognition with auto-reply, and agent screenshot/recognize tools.

Two-way WeChat bridge: reads incoming messages from the local WeChat database and sends replies through Windows UI automation, so you can talk to a local DSH session from your own WeChat. Outsiders who can message this WeChat account can chat with the local session by default (they cannot run commands or touch files); set an inbound allowlist to restrict who may talk to it.

A single-character agent that lives across QQ (via SnowLuma / OneBot 11), Bilibili and Douyin (the Douyin channel needs an always-on Windows desktop): persona cards with slowly evolving traits, per-person memory with Ebbinghaus decay and correction, a virtual clock driving a daily routine, proactive messages, auto-extracted memories, and a ten-tab settings panel covering retrieval, persona, routine, memory inspection, channels, habits, models and usage. QQ groups are deny-by-default: a group is answered only when it is on the allowlist or allGroups is explicitly switched on, and it still has to @-mention the bot. Private chats answer QQ friends only. Bilibili/Douyin auto-reply is off by default, limited to the owner, allowlist and mutual follows on Bilibili, and to the owner and allowlist on Douyin unless reply-to-everyone is explicitly enabled. Vendors MIT-licensed code from dsh-qq-bridge and dsh-douyin-bridge, credited in-source with their LICENSE files; it does not need either installed alongside.

Autonomous Douyin watching in a dedicated Edge browser on Windows (requires Node.js 22.13+): sampling decisions, frame storyboards, danmaku-aware comments, persona memory and a watch diary, all under daily viewing limits. Fork of LockyBee/dsh-douyin-agent — uninstall the upstream plugin before installing this one.

Brings the WorkBuddy, Trae and Qoder desktop logins on this machine into DeepSeek Harness as OpenAI-compatible local endpoints, with an account pool, automatic account switching when WorkBuddy is rate limited, and a settings panel.