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.

Embedded MCP server letting external agents (Hermes, Claude Code, etc.) drive DeepSeek Harness over StreamableHTTP: sync/async task execution, a three-tier file sandbox, a Web-backed approval bridge, session management and search, and path-jailed file tools.

Deep research as an agent mode: one reviewed loop that plans, researches in adaptive parallel rounds driven by the gaps the researchers themselves declare, synthesises a cited report and then reviews it adversarially, instead of a script the model rewrites per call. Questions the round budget never reached are named in the report rather than dropped.

Points web_search at a self-hosted SearXNG instance instead of the native route: pages until maxResults is satisfied, and reports degraded coverage when engines fail so a thin result set is not read as a thin web.

Aggregated web search provider that fans one query out to 11 engines (Exa, Parallel, DuckDuckGo, SearXNG, Brave, Tavily, Serper, Mojeek, DeepSeek, Anthropic, OpenAI) concurrently, URL-dedupes and merges the results. Ships a settings card for toggling backends, storing API keys in the credential store, and tuning concurrency and timeouts.

Progressive tool disclosure: a deferred tool group costs one catalog line instead of its full schemas until the model loads it with tool_search, with one switch per group in Settings and each group measured against the live registry.

Free web search for DSH: anonymous Parallel default plus Exa fallback, a Settings toggle, and an MCP server compatible with Claude Code and Codex.

Adds CC Switch providers and models to DeepSeek Harness, with provider filtering and model-name search.

Memo — session memory search for DeepSeek Harness agents: cross-session full-text recall (memo_search), distilled notes (memo_remember), and corpus stats (memo_stats) over the official sessionQuery service. Zero infrastructure, local-first.

DSH updater + official docs sync in Settings: one-click npm update of @deepseek-ai/dsh with live progress (npm output stream, elapsed timer, monotonic bar), multi-copy protection that only touches the running instance, source-tree mode via git pull, one-click PowerShell 7 install on Windows, incremental sync of the official docs/ with progress, and the dsh_docs_search / dsh_docs_read model tools.

Terminal-style input for the DSH web composer: Up/Down prompt history (prefix search + Ctrl+R), selection toolbar (copy/quote), right-click paste, toggleable chat TOC.

Registers codex-web-search-mcp as native DSH MCP tools (mcp__codex-web-search__codex_web_search / codex_web_research / web_fetch) for model-independent Codex and Grok web search and deep research.

Native tools for an Obsidian wiki vault: wiki_query, wiki_write, wiki_rename, wiki_scaffold, wiki_archive, and wiki_lint cover BM25 search with link-graph context, bookkeeping writes with sha256 source tracking, vault-wide renames, mode scaffolds, source archiving, and health checks — with cross-process locks and optional git auto-commit.

Querit-backed search and fetch providers for the DeepSeek Harness web capability seam (ctx.web)

Browse, search, delete, undo-delete, and update user skills from the Web settings panel; checks GitHub/Gitee Releases for newer skill versions.

Connect dsh to Notion via the official Notion MCP (OAuth + PKCE): search, read, and write pages, databases, and comments through `mcp__notion__*` tools.

GitHub Device Flow connect plus an in-conversation PR workflow: a status bar above the composer for create / AI-review / merge, and github_* tools for search, issue and PR read and write.

Host-side Typert remote for dsh-tool-writing: serves project volumes, chapter status, corpus library, full-text search, evolution entries, and thread-graph data to the client writing panel.

Search-first capability workflow for DSH agents (v1.0.0): reuse local tools or review exact-source plugins before installation, adapt or create capabilities in managed source work, and use receipts that distinguish installed, loaded, activated, and verified states; version tools cover rollback, adoption, and upstream updates.

Toolbox plugin for the Web UI: session/trash/subdirectory/search/preset/config management, tag grouping, long-message collapse, and a scheduled heartbeat with optional IM channel push.

Memory Lake as a persistent memory layer for dsh: memory_search, memory_remember, and memory_forget tools over the memorylake CLI, a session status line, and guided setup/diagnostic skills, sharing one ~/.memorylake identity and memory set with the Claude Code and Codex plugins.

Ollama Cloud native chat adapter: direct NDJSON translation of the Ollama /api/chat wire format, model discovery with context windows and capabilities, and web search/fetch providers under the ollama-cloud id, plus a Web settings card.

Client-side writing panel for the Web UI: project volumes and stats, corpus library, full-text search, evolution version-chain diffs, and an SVG thread graph, shown only in writing-preset sessions.

Replaces the Web GUI trajectory tab with a new-user-friendly round-by-round storyline, plain-language tool labels, category filters and fuzzy search.