Plugins

Per-workspace personal knowledge base for DeepSeek Harness: each identity gets an isolated local library — import PDF, Word, Excel, Markdown, text, HTML and images, auto-chunk and embed into SQLite with FTS5 + vector hybrid retrieval, then ask questions in chat with numbered citations back to the source. Local-first, no cloud upload; vector embeddings need a local Ollama (default bge-m3), and without it retrieval degrades to FTS5 keyword search.

Long-term associative memory for DeepSeek Harness: a local plain-text vault of raw episodes, typed memory cards and entity pages, configured from 设置 → 记忆图谱, and a Memory tab inside a conversation that draws what that session remembered. No build step; the

Local-first, file-backed memory plugin for DeepSeek Harness: Markdown memories, verified trust, per-turn recall, and optional SQLite FTS5.

Local-first, file-native long-term memory for DSH with per-turn preflight, compact context injection, citations, human-approved writes, manual consolidation, nightly report-only maintenance, and a Web panel that is read-only for knowledge while allowing workspace-config edits.

Local three-band memory for DeepSeek Harness: a 24h protection band, query recall and scene replay, injected into sessions without embedding or model calls.

Fully local push-to-talk voice input for macOS: hold a global hotkey, speak, release — transcription is pasted at your cursor. Local-first STT (Qwen3-ASR 0.6B 4bit on MLX/Metal by default, SenseVoice and mlx-whisper fallbacks), zero external APIs, launchd self-healing service and an 8-point diagnose script. The bundled skill lets the agent install, configure (Karabiner hotkey wiring, launchd, engine switching) and troubleshoot the whole toolchain for you.

Local-first research toolkit for DSH: registers kb_grep, kb_list, and kb_save model tools. kb_grep searches the markdown knowledge base with ripgrep when present and falls back to grep, while kb_list and kb_save go through the scoped ctx.fs filesystem service; the KB defaults to ~/dsh-kb. The repo also ships two skills (local-first-research and session-memory) that must be copied into a DSH skills directory yourself; they are not installed by the plugin bundle. The plugin is pure Node ESM with no npm runtime dependencies and ships a framework-free node test harness. Installable via plugin_manager install_bundle; no client UI is bundled.

Adds folders to a running DSH Web workspace from the Windows Explorer context menu and starts dsh web automatically when needed; the menu itself requires a one-time per-user PowerShell installer run from a repository clone (no admin rights).

Project Atlas: a local-first DSH workbench that gives every project a readable name and one-sentence intent, merges duplicate project folders after confirmation, and tidies stale projects without deleting files.

Local-first resume warehouse for DeepSeek Harness: one tool to start/stop the local app and read its health. Everything stays on this machine; the only outbound path is a configurable LLM API.

Life Cards — 把你认识的人和虚构角色写成档案。在对话里问出来，或导入酒馆角色卡；数据是你自己文件夹里的一组 Markdown 文件。

Local document library for DSH Desktop (Windows only, installed with the bundled PowerShell script): upload files once, then every conversation can search and read them through four tools (library_list / library_search / library_read / library_save); upload, download and batch download live in the Settings panel. Files stay on the machine unless you enable the optional vision model, which sends images to the endpoint you configure.

深鲸记忆：跨会话热记忆（每轮注入 MEMORY/USER + memory 工具读写）+ 记忆体检、瘦身归档、记忆包、诊断报告、文档只读。本地明文、零依赖、不上传数据。

Manages archived DSH sessions with native unarchive, a recoverable quarantine, permanent purge, search, bulk actions up to 200 sessions, and 7/30/90-day or never-expiring quarantine retention, without deleting project files.

Hands secrets and PII to the agent without them entering its context, with checksum-validated extraction and masked content classification.

Three-layer memory for DeepSeek Harness — a small always-on core block plus on-demand topic files (profile, preferences, decisions, lessons), with source-annotated writes and supersede-not-overwrite history, so preferences and project constraints stop drifting between sessions. Local-first: no vector DB, no server, no outbound calls.

Local BM25 auto-recall, a fail-closed write guard, a static doctor and a memory panel for an Engramory markdown store. No network, no daemon and no model calls unless you opt in; recall quality is measured by a reproducible benchmark in the repository.

A private memory library for DSH with customizable personas that only records when you ask, storing everything locally in Markdown.

Local-first usage analytics for DSH: subscribes to session events and aggregates tool calls, turns, errors, latency and capability usage into daily tables, shown in a sidebar panel (6 KPIs, 14-day trend, top tools, capability breakdown) and served over a fenced local HTTP API with 18 JSON-RPC methods. Zero runtime dependencies, local mode makes no outbound requests, and no message bodies are collected.

Local-first DSH Web work checklist with rich-text notes, categories, folding, drag reordering, search, JSON import/export, and a restorable trash.

Notes taken from DeepSeek Harness conversations: quotes whole replies or selected passages, keeps highlights rendered at their original position in the session, attaches editable Markdown notes, tags them, filters by workspace or session, and exports Markdown or a full JSON backup stored as local JSON files.

Local decision-layer plugin for DSH: a fail-closed command approval gate and ask/gate tools backed by a 144.3M on-device model. Needs a separate local decision service: `pip install phocinae-server`, then download the ~330 MB weights and keep the service running; without it the tool returns `PHOCINAE_SERVICE_UNAVAILABLE`.

Local-folder knowledge base for DSH: builds a SQLite FTS5 index over Office, text, PDF and scanned files, ships five tools (kb_search / kb_read / kb_list / kb_status / kb_session) plus a Web panel, and retrieves or syncs only when the user explicitly asks.

Local relationship-memory workbench with a confirmation gate: every AI write — extracted memories and newly created contacts alike — lands in a pending queue until the user confirms it in the GUI; materials are archived verbatim with quote-level provenance checks on AI extraction, and confirmed memories aggregate into per-contact timelines, gift occasions and reciprocity views. Ships a native relationship agent preset for conversation capture; JSON storage by default with an optional SQLite backend, zero production dependencies.