Plugins

Diagnoses and repairs DeepSeek Harness on native Windows around the official persistent PowerShell and Workspace Write stack, creates the desktop shortcut, and keeps earlier Git Bash and BusyBox presets behind an explicit legacy setup. No WSL.

Session-scoped GeoGebra canvas with 20 native tools for drawing, scene readback, text layout checks and animation capture, plus 55 mathematical skills and bundled offline applet assets.

baro as a DeepSeek Harness subagent provider: delegate a multi-story goal, get parallel execution, independent review and a verified outcome back — with a live run panel in the sidebar

Base aggregate for DeepSeek Harness Desktop features: Web UI collection, plugin market, Codex Connect, and reasoning controls.

Shared real browser for DSH: a native Electron window the human can watch and take over, driven by the agent over CDP with 20 browser_* tools (open/snapshot/execute/fill/screenshot/download/auth), per-task session isolation, cookie persistence, CAPTCHA detection; self-hosts on plain dsh web without a desktop shell.

The memory that dreams — cross-session memory for DeepSeek Harness: recalls you across sessions, auto-consolidates in its sleep (autoDream), freezes conflicting memories for your review, and keeps a replayable audit trail. Offline-first local semantic search over SQLite with human-editable Markdown mirrors, an entity graph, an interactive memory panel, plus an external API and CLI.

Read-only session work-path observer: fold turns into stage, run, duration and tok/s summaries, then expand parallel branches, tool results and vendor-visible reasoning.

Google Antigravity (agy CLI) models for DSH — streaming chat with Gemini/Claude/GPT-OSS subscriptions, native tool cards, thinking turns, and in-GUI Google OAuth login.

Drive a local or remote ComfyUI server from DeepSeek Harness: comfyui_run / comfyui_object_info / comfyui_workflow tools generate and edit images and videos, with a workflow library (graph extraction: per component / main flow / all), a load area with resolution auto-match, a live queue, SDXL and Wan 2.1 templates, a companion skill, and a same-origin media proxy.

Local-first content production and operations workspace for DSH: manage ideas, scripts, media assets, schedules, goals, publishing status, and post-publication reviews.

Code-first React and TypeScript task apps rendered inline, in Canvas, full screen, or on localhost, with interaction state available to later agent turns and approval-gated MCP and API access.

The memory that dreams — cross-session memory for DeepSeek Harness: recalls you across sessions, auto-consolidates in its sleep (autoDream), freezes conflicting memories for your review, and keeps a replayable audit trail. Offline-first local semantic search over SQLite with human-editable Markdown mirrors, an entity graph, an interactive memory panel, plus an external API and CLI.

Claude Code-style auto-memory, natively: typed memory files (user/feedback/project/reference) with a MEMORY.md index auto-injected into the system prompt (zero footprint when empty); memory_write/read/list/delete follow Claude Code write rules (dedupe-and-update, absolute dates, cross-links); workspace-scoped and user-scoped layers, cross-process file locking with orphan-lock recovery, plain Markdown on disk, no external services, no embeddings.

A DSH plugin for fiction and short-drama production

Red-team engagement mode: send one target organization name and a planner session runs a five-role execution team (recon, asset triage, vulnerability discovery, exploitation, internal pivot) under a user-configurable concurrency limit (three by default, changed from the console and taking effect immediately), preflight-checking skills and resources and asking once for any missing key or VPS first, guided by a built-in first-run onboarding skill; scoring follows the merged intrusion scoring rules (8 categories / 25 points) with server-side caps, highest-privilege-wins and per-service dedup, and self-registered accounts never score — a login that fits no more specific category is scored as controlling a web application system rather than dropped; findings land in a local SQLite fact base with discovery timestamps, shown in a persistent right-side console of 9 tabs that follows the selected session — switch sessions and it shows that session's target organization, resolving sub-agent sessions to their root session and falling back to the session title, the console footer always naming which of the two matched (its per-session binding file, or the title); (asset mapping with a discovery timeline and the live test view, the agent roster with its concurrency setting and editable role prompts, session/tunnel state, findings — vulnerabilities, credentials and access sessions plus the attack files archived against each vulnerability — five-stage attack chain, scoring targets, an evidence-screenshot capability (register a screenshot per score point, at most three representative shots per point so a bulk result such as dozens of endpoints does not flood the console or the report, viewed inline in the console and embedded in the report, with on-site screenshots kept strictly apart from record-generated evidence cards), and a report that spells out how each score was obtained (actions, exact commands, credential provenance, tunnel build commands, a reproduction entry that is either a paste-ready HTTP request or a runnable command, plus success criteria and an evidence index), a category-organised POC/EXP knowledge base, and a skill library that reports for every unusable skill why it is unusable and the concrete steps to repair it); ships 14 reconnaissance/assessment skills (the npm package deliberately carries no tool auto-installer and no attack-chain skills — those ship as a separate toolkit Release attachment that the operator fetches and runs themselves), 56 redteam_* tools and one-command self-update.

AI-assisted local creator workbench for DeepSeek Harness

Let your DSH agent browse Bilibili on its own, read subtitles, write a daily digest, and @ you when it finds something worth your attention.

Execution maze for DSH sessions: the agent's real path — main advance, failed or dead-end detours, backtracks, request retries and subagent branches — drawn on one wall-clock timeline, with three tracks under each lane sharing that axis (tool-call density, token pulse, context pressure) and a deterministic analysis panel below it (tool result matrix, failure-recovery chains, duration distribution); watch it grow live in a session tab, or upload up to 5 session logs for a same-axis compare.

Add a WSL workspace from the web GUI without needing to install dsh or related tools again inside WSL. Bash commands and file read/write operations run within the local WSL distribution on the host machine, while Windows files remain accessible.

DSH session manager: delete with trash/restore/purge, restore archived sessions, recent-activity stats, continue/pause, open log folder, unread markers, fork into a new chat, workspace grouping and sorting, context compaction threshold.

A-share watchlist real-time market monitoring plugin: a collapsible popup in the top-right corner of the DeepSeek Harness (DSH) web interface for real-time quote monitoring, group switching, intraday and candlestick (K-line) charts, and buy/sell target price settings.

Read-only security and compliance plugin for DeepSeek Harness: prompt-injection detection, Chinese-PII redaction, and a local configuration audit with redacted, reproducible reports.

Fluid streaming rendering and smooth scrolling for the DeepSeek Harness Web UI.

A calmer reading view for DeepSeek Harness: native process details, live reasoning, and clean final answers.