Plugin

An annotated browser tab: pages render in headless Chromium on the host and are served same-origin, so you can click an element or drag a region, write what should change, and send the notes into the conversation with selectors, visible text and rectangles. Requires a Chromium-based browser on the host (auto-detected, or set CHROME_PATH / browserExecutable). By default it provides the `browser` tab type itself; set `takeover: false` to keep the stock browser and use a hand-off button instead. Picking continues until you press Esc.

Right-sidebar browser for DSH Web: renders public sites over CDP, local/dev pages through a same-origin proxy, emulates desktop and phone viewports, and turns element picks into chat annotations. Fork of zengxiaolou/dsh-annotate-browser (MIT), install one or the other — both add their own right-sidebar browser tab and drive a separate Chromium. Requires DSH 0.2.1-rc.2 to 0.2.x, Node.js 22.19+ and a Chromium-based browser on the host (auto-detected, or set chromePath).

Adds a right-click command "通过 dsh 打开" (open with dsh) to the Windows Explorer right-click menu for a folder, a folder's empty background and any file: it launches DeepSeek Harness on that folder, creates a new session every time, and puts the clicked file into the new draft as an @ reference. Ships a packaged-COM menu for the Windows 11 modern menu plus a registry entry for the classic menu; first install asks once for a certificate trust (native/trust-cert.bat).

Chat-first draw.io plugin: the agent creates, reads and edits native .drawio files, an interactive draw.io viewer renders them in the transcript, and the diagrams live under the workspace's diagrams/ directory. No draw.io account, no npx MCP server, no local editor install.

Bridges the official COROS MCP server into DeepSeek Harness with a self-contained local stdio-to-HTTP bridge and on-device OAuth login, exposing 34 COROS tools on the current endpoint for sleep, HRV, resting heart rate, recovery, training load, activities and FIT files, plus workout and training-plan CRUD and scheduling.

Traces how something became what it is, what it currently rests on, and what it will become next.

File dedupe and unify toolkit, shown as "小视频整理" in the DSH sidebar: exact matches by head/middle/tail sampling or full byte compare, near-duplicate MP4s grouped by duration and a configurable first-N-seconds frame window (default 10s, 1–5 fps, default 2; longer videos are compared on their first N seconds too), batch rename or move by extension, UUID, file size or video length, empty-folder cleanup under the selected sources, and MOV/AVI/WMV detected by file header and transcoded to MP4 keeping resolution, frame rate and audio parameters. Requires ffmpeg and ffprobe on PATH. Concurrent workers per task with a shared setting; one task at a time; per-group help dialogs; local-only API. Every task that moves files has one-click restore: per-group/target _dupfc_restore.json records, deleted files skipped and counted, files outside the record renamed to UUID and moved into resetFail; orphaned ffmpeg processes left by a crashed host are swept on plugin load.

Host-side HTTP bridge on 127.0.0.1:39217 with a Bearer token stored at 0600: external processes can create real DSH Desktop sessions that appear in the workspace sidebar, send prompts (queue or steer), read state and the last assistant reply, list workspaces and sessions, and long-poll until a turn finishes. Zero runtime dependencies; fixed loopback port; no outbound network; message bodies are never logged.

Connects DeepSeek Harness to LRC's local structured memory: distills conclusions every 8 turns, drops near-duplicates by character-level Jaccard similarity (≥ 0.85), and writes them to a local LRC store. Five tools — lrc_recall, lrc_forget, lrc_remember_now, lrc_handoff and lrc_status — cover on-demand recall, retracting wrong entries, immediate writes, session handoff and a status line. On first run it downloads a per-platform LRC binary (win32-x64, darwin-arm64 or linux-x64, SHA256-verified) and starts an isolated instance, so the LRC desktop app is not required; data stays in $DSH_HOME/cache/lrc-plugin/data unless LRC_BASE points at an existing instance.

Long-term memory for DeepSeek Harness agents: per-turn archival and recall, two-phase consolidation of the per-day scene log (the host prompts every five unconsolidated rounds and the caller confirms with an ackToken), and validity, weight and expiry as three independent functions.

Connects DeepSeek Harness to the hosted Renor memory MCP server over Streamable HTTP, using a Renor API key from RENOR_API_KEY, so the model can call Renor's recall and save tools. It is a configuration bundle with no code of its own.

Five-layer persona (L1–L5), event memory with FTS5 plus Dice retrieval, cognitive filter, skill cards with auto-frozen asset packs, millisecond reflex rules, three-tier safety degradation, a read-only brain star map, and an optional VPet-Simulator MOD bridge.

Per-project long-term memory for DeepSeek Harness: a panel to browse, search and edit what each project knows, and a pointer injected after the first user message telling the agent to read the handoff pack. The memory store itself is a local MCP server (Python + SQLite) in the same repository; install the plugin from npm, then clone the repo, set up the MCP server per the README, and the plugin locates the checkout through DSH_RAG_ROOT or a common install path. Handoff packs are ordered for prompt-cache reuse: stable baseline first, facts appended at the end.

"Oh, you're finally here. I've been waiting for you." A plugin that brings Elysia into DeepSeek Harness. Once installed, she remembers you: what you said last time, what you care about, so every new conversation picks up where it left off. Memory lives on your own disk, mirrored across two drives, shared by every session and editable by hand. She speaks the way she actually speaks, measured from 1,696 officially confirmed voice lines rather than a hand-written character sheet. One-click voice setup: the plugin downloads the 200 MB voice weights, places them correctly and fills in the paths for you (the 27 GB engine itself must be installed separately, and needs an NVIDIA GPU). She also drops a WeChat-style bubble with her avatar after finishing a task so you can tap to listen, sends stickers when the mood fits, and learns the runbooks you give her. Memory pack, voice, and stickers are all off by default.

Ship OpenTelemetry GenAI observability and multi-device cloud state sync from one DSH bundle. It reuses and replaces the standalone @loongsuite/dsh-plugin (traces + metrics for sessions, agent loop, LLM and tool lifecycle; do not install both — disable or remove the upstream plugin first), and adds a WebSocket client that pushes full session event logs (header + snapshotEvents) to a relay you run so different local DSH instances share state. On connect it pulls and rebuilds the other devices' sessions automatically (cross-device resume). The sync client itself has zero third-party runtime dependencies; a small Node.js relay is included in the repo. The local /cloud-sync/* HTTP routes (status, sessions, config, resync, delete) have no origin or loopback check, and the bundled relay accepts unauthenticated connections unless AUTH_TOKEN is set — keep the DSH web port off untrusted networks and run the relay with a token.

Spotlight & IntelliJ-style centered search dialog for sessions and chat messages, replacing sidebar search.

Conversation map for the DeepSeek Harness web GUI: one page per workspace, conversation cards placed freely, links between cards, named and colored boxes that group conversations, high/medium/low priority marks, a picker for which conversations (archived ones included) are on the map, and a file-based API so another conversation can rearrange the map.

Bookmark a whole assistant reply with the star on its action row, or bookmark any selected sentence with the icon beside the selection; pins are saved as Markdown to a local folder or an Obsidian vault, and the existing right sidebar lists, tags, searches, exports and jumps back to them.

Adds a four-part reply-formatting contract to the system prompt, so every answer is laid out like a Xiaohongshu post: a conclusion-first hook, a star-rated comparison table, emoji-headed bullets with four to six concrete steps or numbers each, numbered sections grouped by entry threshold, images that each carry a caption and one source link, and a banned-word list covering nickname terms, hype words and marketing catchphrases. Code, commands, paths and formal documents keep their original formatting. Host-only static prompt section: no config, no client UI, no dependencies.

Yugan Huafang (语感花房) is a personal voice workshop for DeepSeek Harness: your own writing and corrections become explainable local style rules, optionally distilled by the current model, then compiled into a preset you pick per session; edits apply on the next message in that session.

DSH plugin: bring your ChatGPT subscription into DeepSeek Harness — Codex models, GPT Image, quota and recovery checks, plus a per-plugin scoped HTTP(S) proxy. Community alpha fork of dsh-codex-connect, published on the alpha dist-tag; it registers the same openai-codex provider, so it cannot be installed alongside the upstream plugin; the image, quota and proxy features are opt-in and off by default.

Adds the Miaoshou (Meituan CatPaw) desktop client as a DeepSeek Harness model provider. The 12 models mirror the ones the Miaoshou app picker shows, each carrying its credit-cost multiplier; thinking levels are translated into the upstream modelParams; a read-only panel reports available credits and the current plan. Sign-in is a QR link, so the desktop client does not have to be running.

Adds ChatGPT sign-in, Codex subscription quota (5-hour and weekly windows) and Codex-backed web search to DeepSeek Harness; installing it switches the profile's web search provider to openai-codex.

Hides the signed-in deepseek-account model group from the model picker and rewrites an already-saved account selection to deepseek-official in prepareCall and stream, so a stale conversation cannot spend on the account; no settings page and no runtime dependencies. Requires an official API key configured under Settings → Models first — without one there is no model left to select after the account group is hidden.