Plugins

Karpathy LLM Wiki pattern knowledge base for DSH: wiki-write/wiki-search skills, zero-dependency pipeline (lint/index/mnemon memory sync/quality feedback), minimal lifecycle plugin injecting schema + knowledge preview, SiliconFlow semantic recall via an Ollama-compatible proxy.

Fold completed turns into their final conclusions, split thinking from prose with a divider, and jump between turns from a rail dockable left or right with line or dot marks, an optional ring and hover summaries; it can hide the host right-edge TurnNavigator, load earlier history, and open a pre-filled diagnostics issue.

Compact right-edge turn rail with hover summaries and click-to-jump navigation. Ships on npm as `dsh-turn-scrubber`.

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).

Connects DeepSeek Harness to Busabase: search workspace knowledge, work with structured records and apps, submit writes as reviewable ChangeRequests, and inspect results in live cards.

Native Graphify knowledge graph plugin providing 10 code intelligence tools, topological search, god nodes discovery, and PR blast radius triage.

Right-edge user-message navigator with an adaptive block layout that fits the available height, plus hover previews, keyboard controls, and click-to-jump navigation.

Left-edge user-Turn navigation rail with reading-position highlighting, hover previews of per-turn metrics and model-answer excerpts, keyboard and click-to-jump controls, and local conversation search.

Conversation node navigation rail for the DSH Web UI: one dash per user message on the right edge, reading-position tracking, hover preview card, click-to-jump with highlight line, sliding window, and auto-hide.

DeepTutor tutoring bridge: deep explanations, self-test questions, learning-path planning, personal knowledge-base search (RAG), and note archiving via deeptutor_run / deeptutor_kb / deeptutor_note tools.

One memory layer for every AI tool and agent: Context Bundle injection, prompt-time recall, MCP tools, and turn-end DSH thread capture.

DeepSeek Harness adapter for Context Mode: in-process ctx_* tools for sandboxed code execution and an FTS5 knowledge base, plus context-window routing guidance.

A persona and memory plugin for DSH Desktop. Distill characters from chats, novels, scripts, or character sheets; keep long-term and temporary memories, learn style corrections and approved replies, detect persona leakage after switching, visualize memories, and import or export persona cards. Task guidance is reduced to one lightweight fixed discipline with no plans, ledgers, or dynamic reminders.

Runs TiddlyWiki 5 as the DSH persistent knowledge base: ten tiddlywiki_* agent tools (filtered search, read/write/batch/rename/delete, recent, tags, git sync with conflict resolve), a full TiddlyWiki editor embedded in the GUI center column over a same-origin proxy, a right-side wiki tab, a per-session tab summarizing the notes a session read or wrote, a quick-note card with draft auto-save, and an optional clip bookmarklet with image attachment — all backed by an auto-committing git repository.

A governed swarm of six specialist DSH agents — orchestrator, planner, knowledge-base bridge, developer and two reviewers — turns a requirement into a strict phase pipeline where every delivery must prove itself with structured evidence before the next phase may start; reviewers are read-only, code merges only after a review pass, and an append-only event log gives full replay and audit on a live kanban board. Its design draws inspiration from the Hermes Agent kanban.

Scroll-painting message rail for DeepSeek Harness: a slim right-edge rail with one indicator per user message, scroll-spy follows the reading position, hover unfolds a canvas with full message previews, and clicking jumps to any history message; animates in sync with better-sidebar panels.

One shared Obsidian vault for every agent: dependency-free Python core (search/promote/adjudicate/forget), vault template, dsh plugin (memory_search/show/submit/status).

Compact right-edge turn rail with hover summaries and click-to-jump navigation.

QQ channel plugin for DeepSeek Harness over OneBot v11/SnowLuma, with pairing-based access approval, long-term memory, a knowledge base, proactive events and an admin panel.

Read-only semantic retrieval for meow-memory: a local bge-m3 vector index over memory entries and conversation turns, a knowledge graph, and verbatim turn recall. Never writes back to the memory store; requires meow-memory.

QQ (NapCat / OneBot 11) bridge for DeepSeek Harness: chat with your harness from QQ, with persona presets and custom personae, a grouped sticker library plus web sticker search, edge-tts or custom HTTP TTS voice notes, pluggable lookup engines, periodic memory compaction, an owner-only relay mode, and an eleven-tab management panel with live monitoring and per-turn cost tracking.

Desktop half of the dsh browser extension: mounts a token-authenticated WebSocket bridge on the dsh webserver and exposes the browser_* tools that let the model read the tab you are on as text and act on it, with image recognition off until the user enables it.

OneBot v11 hub: sits between an upstream OneBot implementation (LLOneBot and similar) and downstream bot implementations, relaying events and actions verbatim, and gives the agent a per-session timeline, an action ledger, layered memory (active topics and tasks, long-term events, person and group profiles) and onebot_* tools for replying, media, members and raw API calls.

DSH adapter bridging DeepSeek web chat and DeepSeek Harness with automatic DSM-tag harvesting, memory injection and write-back, full-answer saving on the web, a DSH sidebar for browsing and manual injection, named-entry retrieval, general/non-general classification, and transactional memory compression; works with the separately loaded Chrome/Edge extension in extension/ and the local @zoria-lind/dsh-ecolink-service, which the adapter can start automatically.