Plugins

Project-scoped persistent key-value memories with set/get/list/delete/search model tools and JSON-file storage.

Attach tags to sessions and search sessions by tag in the Web settings panel.

xAI Grok subscription chat: SuperGrok or X Premium+ OAuth, a displayed model subset, Responses through the Grok CLI proxy, and always-on server-side web_search and x_search.

Look & theme plugin for the DSH Web UI: built-in palettes, light/dark/follow-system appearance modes, Open VSX theme search & install, and VS Code theme import with a persisted theme library.

Interactive terminal chat app for dsh: streaming conversation, tool cards, jobs panel, full-text search, trajectory replay, multi-session tabs, and A2A dispatch (Ink-based).

Installed-plugin catalog for DSH: group plugins by origin (official vs self-installed) in a searchable panel with enable/disable, uninstall, and one-click update.

DeepSeek Harness plugin: every user prompt you type (in the web UI) is appended to your atuin shell history, so it shows up in atuin search and shell integration.

fastCRW-backed web search and fetch providers for DeepSeek Harness (ctx.web)

Bridges the LiuHe MCP code toolkit (44 tools) into dsh web: repo_map, symbol search, edit_batch with tolerant matching, transactional edits with undo journal, and deterministic quality gates — backed by a crash-isolated Rust tree-sitter parse daemon and SQLite index.

Bridge the vercel-labs/skills ecosystem into dsh: LLM-driven skill search, install, and lifecycle for temp/project/global scopes

SearXNG-backed web search provider for the DeepSeek Harness web capability seam (ctx.web) — self-hosted metasearch, no API key, no model turn per search

DeepSeek Harness plugin: AnySearch-backed web search provider (aggregates exa/tavily/firecrawl via one MCP gateway) registered into ctx.web.

Persistent long-term persona memory for DeepSeek Harness: MEMORY.md/USER.md storage, memory + memory_search tools, per-request context injection, and secret scanning. Ported in spirit from pi-hermes-memory.

Tavily search provider bundle for DeepSeek Harness (dsh): registers a WebSearchProvider into ctx.web

DSH skin plugin: Alphacoders popular wallpapers as the DeepSeek Harness Web GUI background (gallery, search, local image upload, light/dark mask)

DeepSeek Harness plugin: Nocturne Memory client — automated long-term memory (boot/read/search/create/update) backed by your own Nocturne MCP server.

The `dsh pm` plugin manager: multi-source search (awesome list + GitHub + npm), install/remove/update per profile, and a doctor audit of manifests, bundle patches, and version drift.

Per-agent on-demand tool discovery and progressive schema disclosure.

Cross-session memory for the model: full-text search all past sessions (SQLite FTS5 via ctx.sessionQuery) and bring the strongest matching excerpts back into the current context.

Registers 36 bundled agent skills (research writing, LaTeX, experiments, design review, office documents, animation, Windows shell and dsh plugin conventions) as one host-only skill provider with no UI, no network calls and no telemetry of its own; skill scripts run with the user's permissions only when invoked, local skills of the same name take priority, and uninstall removes all 36.

Browse and search Tencent ima knowledge bases, read files in an in-panel dock, and add links, files and notes via the ima OpenAPI.

Connects all seven Qwen Token Plan Harness-entitlement MCP services (enhanced search, web fetch, code interpreter, vertical search, image, TTS, ASR) plus the decision-model-preview model (qwen_decide) as native tools, with a per-service on/off and live-status panel.

Confluence and Jira over Atlassian remote MCP as a configuration-only bundle: one MCP client row, OAuth handled by mcp-remote with the token cached in ~/.mcp-auth, no login command and no in-app UI. Exposes mcp__atlassian__* tools (CQL search, pages, comments, JQL issues, transitions).

Long-term memory ported from the OpenAI Codex memory pipeline: sessions idle for 6 hours are extracted in the background by a chosen model, then merged by a hidden agent into a Markdown memory folder at most every 6 hours; new agents get the memory summary in the system prompt plus four tools to list, read and search memory and save corrections. Models are chosen on a settings page or with /memories; an optional filter keeps a notes folder out of memory.