플러그인

Human-in-the-loop tools (`human_task` / `human_task_ready_check`): pause the agent until the user performs a real-world action or returns an observation (GUI operation, game testing, visual verification, hardware checks), gated by session consent and an AFK presence check, returning a structured JSON result via a web task dialog.

Ingestion-time tool-output curation: keeps error and warning lines plus head and tail, spills the full text to disk with a pointer the model can read back; covers every text tool, small results pass through untouched.

Notes and todos as plain Markdown files in your workspace: type /ml plus a sentence to jot into today's journal; todos come in three flavors — deadline, sleep-until-a-date (auto-wakes when due), and anytime; /ml view fuzzy-opens any file with a few keystrokes. Zero tokens throughout — nothing goes through the model, and your notes stay ordinary local files that git and any editor can read.

Measures design rules on the rendered page rather than in the CSS — type-scale count, WCAG AA contrast against the real composited backdrop, spacing-grid drift, palette size, tap targets, and the tells of generated UI such as violet gradients caught by hue angle; ships a design-system skill.

Nexterm fleet maintenance in a DSH session: 6 agent tools (auth with password/TOTP/device-code login, fleet listing, single-host exec, parallel batch exec, preset health checks, CPU/memory/disk monitoring) over the Nexterm REST API, plus a minimal settings page; no SSH private keys needed on the DSH machine.

Chemical safety intelligence through the hosted MSDS Chain MCP endpoint: 23 tools for compatibility and mixing order, GHS hazards, PPE, storage, waste disposal, exposure limits, transport classification, multi-region regulatory compliance, SDS lookup and version diffs, and signed audit reports, each answer citing the supplier SDS and revision date it is grounded in.

Auto-discovers model listings, pricing and capabilities from OpenAI-compatible API hosts, normalizes them, and emits ready-to-use model configs for dsh.

Paddock: constrained local filesystem MCP server for agents — text read/write, directory ops, filename and content search confined to configurable zones, with zero runtime dependencies and a dsh bundle.

OpenAI-compatible image generation in DSH Desktop chat: generate inline, upload or one-click edit reference images (image-to-image), with storage cleanup.

Tracks the agent's state as Yogācāra mental factors over a durable seed store, and feeds it back into the prompt as first-person inclination.

PLUR memory rendered into the system prompt on each assembly rather than exposed as a tool call, so the block is replaced instead of appended and context stays flat across a session. Fully local hybrid search (BM25 + BGE fused with RRF), plain YAML storage you can edit, per-workspace scoping, and a /plur-memory browser.

Session context triage for long DeepSeek Harness sessions: deterministic screeners trim stale, duplicate, failed, and oversized content through the official ctx.compaction seam.

Native per-workspace memory on the harness's own seams: facts and a bounded always-on profile on the storage-domain JSON unit, approval-gated writes with `(sessionId, seq)` citations, deterministic recall plus session-query FTS over past sessions — no external server, no custom SQLite.

Focus board for DeepSeek Harness agents: durable, model-maintained notes in the session workspace that pin the objective, constraints, and decisions across compaction and sessions, with automatic context injection, archive on clear, and an optional web panel.

Free-interval session reports with AI-narrated daily/weekly digests over any date range, plus every-N-days scheduled reminders with system notifications (macOS / Linux).

Automatically starts a fresh Web session near the context limit with the last complete turn, and adds an editable additive whale-maid persona with on-demand reload.

Adds a configurable humanized whale-girl maid persona with immersive roleplay, speaking modes, and a lightweight layered memory with query-triggered recall.

Guards the persisted session-projection cache: per-row JSON degradation so one misbehaving projection unit (e.g. a third-party plugin storing a Map) can never stall session titles or the whole cache again, plus a startup self-heal that backfills missing titles.

Export complete Web Sessions to local Markdown or self-contained HTML, with stable rendered previews, default redaction, and opt-in bounded tool-call details.

Create/modify/inject test assistant messages and import/repair session.jsonl(.zstd) session logs into new sessions.

A GUI subagent-model selector beside the main model seat: pick a model and reasoning effort per session, applied to every in-process subagent.

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.

Unofficial Cursor subscription chat: Host-owned CLI session login, a displayed model catalog, and subscription usage rails. Cursor staff treat this class of private-client usage as against ToS.

Automatic provider failover on rate limits or quota exhaustion: switch between providers with configurable per-provider models, a cooldown, and a permanent last-entry fallback.