Plugins

RunningHub cloud ComfyUI workflows as a background task pool: submit a batch, and a watcher dispatches it within a concurrency budget, polls each job, downloads every output to disk, and wakes the session when the pool drains. A shared ledger records batches, costs, instance tiers, submit and finish times, and per-file save paths, with a live board in the right sidebar.

Turns real DSH crash logs into a short hard-constraint list: static preflight before a plugin installs, conflict check afterwards, controlled self-heal when the harness will not start — plus handing a huge session over to a fresh one, the brief written by a model that reads the original transcript.

JetBrains-style Git workbench for DSH: hunk and line-level staging, side-by-side diff with word-level highlighting, commit graph and branch operations, three-way conflict merge, and commit messages drafted with the host model.

DeepSeek Harness (DSH) plugin: injects a bounded, timestamped snapshot of your local Second Brain (identity + state fingerprint + pointers) into every new session's prompt. Read-only, zero-write, fail-loud, zero dependencies. 第二大脑载入器：让每个新会话开局自带记忆快照。

DeepSeek Harness 原生推理档位银河滑块

Standalone QQ-bot extension pack for DeepSeek Harness — fully independent, no other plugin required. Two-layer SQLite memory with hippocampal recall, a persona that keeps learning from daily chats, group tiers, local-model quick replies with a single-brain arbiter, TTS outbox, sticker library, an approval-gated video studio, and a four-form desktop pet (three custom characters plus the stock fish) playable over a public invite link with access-code login, single seat and brute-force protection. Chat bridging is deny-by-default: c2c/group access defaults to a care mode that only responds to the special-cared people and groups of the owner (shared with the persona system, zero extra config); allowlist, open and disabled modes remain available. Requires QQBOT_APPID and QQBOT_SECRET, and Node.js 22.5 or newer.

Local GPT-SoVITS text-to-speech for DSH: reads replies aloud, switches voices from the right sidebar, and trains a new voice from a dropped audio sample. First run downloads an 11.4 GB engine and needs an NVIDIA CUDA GPU.

Reads your past DSH conversations and surfaces recurring prompt gaps — missing paths or versions, an unstated output format, missing preconditions that break tool calls — each with a paste-ready rewrite. Adds a one-click rewrite next to the composer that applies those constraints to the draft in a shorter form.

Dual-brain agent presets for DSH: one model plans the framework and delegates execution to a subagent pinned to a second model. Ships brain-ds (DeepSeek-V4.1-Flash plans, MiMo-V2.6-Flash executes) and brain-mimo (the reverse), switchable per session. Needs two providers configured (Xiaomi MiMo and a DeepSeek account), and the main brain must be selected manually.

Read-only Raindrop.io dashboard in the sidebar with collection and tag distribution, top source domains, content types, a 12-month trend and a cleanup backlog, plus two read-only agent tools for analyzing saved bookmarks. Requires a Raindrop.io API token (create an app and paste the token).

Distills daily AI conversations (Doubao, ChatGPT, DeepSeek, Kimi) into structured Markdown notes in your Obsidian vault.

Adds a Matrix-inspired digital-rain startup animation for DeepSeek Harness, a rectangular light portal that opens to both sides, optional replay when the desktop window reopens, and a green UI theme with adjustable hue.

A prompt optimizer in the composer input tool row: pick a category and a template, then ✨ rewrites the draft in place with one-click undo. Pick from the Basic, Context and Image categories; you can cancel a run, and it shows elapsed time and token usage. Ships 15 templates covering task-instruction rewriting, step planning, safety-research framing, system-prompt role cards, and text-to-image / image-to-image prompts; context templates read the recent turns of the session for coreference resolution. Calls go through the host model service, and a settings section exposes the model and the budgets. Output guards check that user-written constraints survive, warning rather than auto-retrying. Adapted for dsh 0.1.7 and 0.2.

Compiles a rough need into a versioned task book (goal / context / constraints / acceptance / decisions / open gaps, all numbered) and hands it to any AI window losslessly: the receiver must pass a read-back handshake — restate, list gaps, declare READY — before work starts; /answer closes gaps with an automatic version bump, /forge-list tracks which window holds which version.

Use ChatGPT Codex, Claude, Grok, Antigravity, Kimi, GLM, Cursor, Kiro, Copilot, Qwen, ERNIE, Spark, JetBrains, Perplexity, Replit, and Cody accounts as DeepSeek Harness LLM providers via OAuth.

Speaks your agent's reports in a voice you choose, compressing long reports before speaking. Character voices need no training - a 3-10 second reference clip clones one, and community-trained models work too - and no 6.4 GB GPT-SoVITS install: the plugin installs its own runtime and voice. An existing GPT-SoVITS can be used instead, and it is the same voice model.

Publishes a lesson into the DSH conversation: the dependency spine, the question and the vault's drawings, drawn in the vault's own palette.

Persistent project intelligence and memory plugin for DSH: architecture analysis, cross-session context, TODOs, and optional hybrid retrieval

Coding retrospect distilled memory for DSH: distills rejected solutions, pitfalls and constraints from each turn via a local LLM, tags them into MemOS (type:rejected_solution), and boosts weighted recall on coding tasks via agent/pre-step.

Force the agent's chain-of-thought, planning, tool-invocation reasoning, and internal deliberation to stay in Chinese — the language constraint is injected at the top of the system prompt before every reasoning step, so it cannot be diluted by tool-returned content. A settings panel lets you edit the constraint text on the fly.

DeepSeek Harness plugin: GitHub repository/issue search, repo and issue details, and file reading tools (github_search / github_get). Anonymous by default; an optional read-only fine-grained token unlocks code search and raises the rate limit.

A QQ NT messenger skin for DeepSeek Harness: light and dark share one QQ NT language — clean restrained light mode (brand blue #12B7F5, light-blue bubbles) and a calm blue-gray dark mode (#101822) — applied as reversible token and layout layers that never touch your Light/Dark preference.

A cozy offline vocabulary trainer for the whole family: 1094 curated words, spaced repetition, 6 quiz types, spelling games and a lazy large-screen mode; opens as a sidebar panel and also runs standalone as one HTML file.

Terminal-style AI-lab idle game where you hoard compute, train and upgrade models, publish papers, and prestige from neural nets to ASI.