Plugins

Stores the agent's long-term memory as plain Markdown in an Obsidian vault — every memory is a .md file with YAML frontmatter that Obsidian indexes natively, so you can read, edit, link and back up it with tools you already use. Nothing is locked in a database. Ships a sidebar panel (tag filter, sort by recency or importance, edit in place), 7 agent tools, three-tier token-budgeted recall, BM25 ranking (no embeddings, no API key, works offline, CJK bigram tokenization), importance decay with archiving (moved to .archive/, never deleted), and optional GitHub Contents API sync. A note containing a secret is refused rather than redacted, because a redacted memory reads as complete while the important part is gone. Zero runtime dependencies; everything comes from the DSH host.

Fills in a cheaper sibling route for subagent calls that name no provider, model or effort (for example Opus to Sonnet 5.5 at medium, Qwen max to Qwen flash); explicit choices and subagent_fork are left alone. Requires the subagent-model-selection policy to be enabled with the target route in its allowedModels - without it the plugin does nothing.

Adds a Speed setting (Standard, Fast, Ultrafast) for OpenAI and Codex models on a patched dsh build: the pinned dsh 0.2.1-alpha.2 web client needs the Model / Effort child-slot patch, the host pi-ai must be 0.87.1 or 1.1.0 (other versions refuse to load), and the terminal controls need a patched dsh-TUI. Then it appears in the Model / Effort menu; in dst /speed opens a picker or sets the speed directly, and the current speed shows in the bottom bar. The choice is kept per session, provider and model and is sent as the request service tier.

Skill bundle for tiered multi-agent science campaigns in math, physics, astronomy, engineering, and biomedical evidence: a shared blackboard, independent verifier and red team, wolf-pack and flanking tactics, token and time budgets, known-answer evals, a four-agent pendulum pilot, and a six-agent fourth-order pilot that caught and corrected a benchmark answer-key error. Does not claim open-problem solutions.

Disk-backed persona card, handover note and long-term memory for DSH agents; each new session reloads them, and every memory carries a source tier, stamped revocation and soft archive.

Local long-term memory for DSH sessions: archives older turns under context pressure, with four tiered hot-memory boards, project documents, memory families with editable family names and root transfer that preserves project hot memory, summary keyword locator with segment-level candidates and paging, manual injection, 20K segmented reads, and tag-related retrieval. Includes staged recall cues and post-install version verification. All data stays in the workspace.

Standalone DSH plugin: Codex/Claude continuable CLI subagents, wait_subagent, child exit guard and model tiers. Pure ESM, no build step.

Advisory permission checks for DSH tool calls: risk tiers, a path sandbox (empty allowed_roots denies every path-like call), a per-minute call limit and a JSONL audit, exposed through gate_check / gate_check_path / gate_policy and ctx.gate — other plugins or prompts must call the gate; it does not intercept tool calls by itself.

Long-term notes and daily journals kept per workspace in a hot/cold archive, each tier with its own index and rebalanced once a day; read and written through seven memory_* tools, with a settings page for per-workspace options.

Six-tier memory plugin that captures each conversation turn, injects a stable memory block as a user snapshot, and compacts the host's own history into a single placeholder without calling a model.

Picks each subagent model from the local catalog by task category, unless the caller already named one. Free and quota tiers are ranked together by per-model capability tags; a pricier model is used only when no cheap model is tagged as good at that kind of work. Only providers whose remaining balance is readable, or that are account-backed, enter the candidate pool; the rest stay listed but are not routed. A panel adds per-model manual priority above the automatic order plus allow/revoke controls.

A personal usage profile page in the DSH sidebar. Five headline numbers (cumulative tokens, today's tokens, longest task, longest and current active-day streaks), a 12-month activity heatmap with daily / weekly / cumulative scopes, a Cache Lens that splits every token into cache hits, uncached input and output as a segmented bar (with a zoom into the uncached split), a stacked bar chart of tokens over time grouped by model family (version plus tier, so vendor-specific ids and unversioned aliases collapse correctly), and a per-provider split for today or all time. A page-level range (all / today / 7 days / 30 days) drives the token figures. Everything is folded from this machine's own session logs through ctx.sessionQuery. The only outbound request is a six-hourly read of this package's own version from the npm registry, used by the in-panel update button — no telemetry, no credentials, nothing uploaded.

A WebSearchProvider that falls back across backends instead of relying on one: Exa, then Bing HTML, then DuckDuckGo HTML, and only then the quota-limited SerpAPI, so the free tiers carry routine searching.

Shows per-turn, per-session and per-workspace conversation costs in CNY, priced by DeepSeek's official tiers with peak/off-peak hours and per-request Search/Fetch billing.

Adds a writing console above the composer with four style tiers (T1-T4) and five rigor tiers (L1-L5), selectable by hand or left to automatic choice; keeps project terminology and banned phrasing in .mem/config.md with a read-only human section; and provides a whale_polish tool that rewrites expression without changing facts.

Standalone QQ-bot extension pack for DeepSeek Harness — fully independent, no other plugin required. Two-layer SQLite memory with hippocampal recall, a persona that keeps learning from daily chats, group tiers, local-model quick replies with a single-brain arbiter, TTS outbox, sticker library, an approval-gated video studio, and a four-form desktop pet (three custom characters plus the stock fish) playable over a public invite link with access-code login, single seat and brute-force protection. Chat bridging is deny-by-default: c2c/group access defaults to a care mode that only responds to the special-cared people and groups of the owner (shared with the persona system, zero extra config); allowlist, open and disabled modes remain available. Requires QQBOT_APPID and QQBOT_SECRET, and Node.js 22.5 or newer.

Per-Session OpenRouter routing: a loopback relay writes `service_tier`, `provider.sort` and the `:floor` variant into each request from one of nine presets picked on the composer chip, with a pinned base URL per preset for route-level defaults.

Rates how hard the current message is and shows the cheapest model and reasoning effort that still fits, above the composer, before you send.

Sidebar account-balance quick view for DeepSeek Harness: balance, bonus credit, current model and the official peak/off-peak pricing period, with ruby/amber/jade/gold tiers and a low-balance warning.

Cross-session memory for DeepSeek Harness: a three-tier store (behavior notes, deep details, session archive) plus a 600-character core card injected every step, work/companion/learning state lines, multi-person and multi-group records with visibility partitions, session-scoped suppression or deletion of memory fragments, summaries and fact candidates that can route to a separate model, and backup plus self-check tools. Data is plain text under the home directory, and entries can carry images and audio stored by content hash.

Yijing-based decision review plugin for DSH: six-layer weighted aggregation engine (384 yao to taiji) with strong-association veto rules, pure JS with zero solver dependencies. Free tier is capped at 9 runs per day and activation codes raise it; the stock-trend scenario pulls live quotes from Tencent for the stock codes in the request.

Union IM bridge for DSH — an independent implementation uniting the capability sets of community peer plugins (xmanrui/dsh-im, MichengAI/dsh-im-connect). Drive your agent session from 15 channel adapters across 12 platforms (including email; WeCom/DingTalk/QQ each contribute two: bot + self-built app or notify tier) — WeChat (official iLink QR bind), Feishu/Lark (long-connection + streaming cards; the voice tier requires system ffmpeg), Telegram, Discord, WeCom intelligent bot & self-built app (signed callback), DingTalk (stream + AI Card and custom-robot notify), QQ official bot (plus notify tier), Slack (Socket Mode), WhatsApp (Baileys QR pairing; the dependency ships as an optionalDependency of the plugin package), Matrix, iMessage (macOS only), Email (IMAP/SMTP thread routing). The cross-version narrow waist auto-adapts settings gen1/gen2/gen3 across hosts 0.1.2-rc.1→0.2.1-rc.2 (12-tag enum; rc.2 verified by a real desktop-profile install with double read-back) using capability probing only, never version branches. In chat: a 25-command panel, tool-approval and question loops answered in the originating chat (deny-by-default, initiator-only, 5-min expiry), image/file input gated on host model metadata, deliverable file return, a delivery log with bounded retry (uncertain is never re-sent), proactive delivery and fragment composition. It also splits the native sidebar into self-owned Tasks / Channels tabs (standing down entirely when another plugin already owns the slot), registers an `im-concise` agent preset plus reply sanitisation that keeps GenUI fences and raw HTML out of text-only chats, renders `svg` fences to PNG images, guards model choice with an allowlist, and mirrors each turn's final answer to notify channels via `/relay` (addressed by account ID or alias, never guessed on ambiguity). Secrets are one-way into the vault and never echoed back. npm: `dsh-im-union`.

Task-tiered session notifications for DSH: marked main-line sessions alert as they finish, other sessions batch into one summary, plus balanced and silent modes; per-event sounds or uploaded audio, per-session mute, click-through notifications, and an option to wait for subagents.

Tiers free-channel models into three 1M fallback chains plus a custom chain; orders them by measured throughput, drops models below throughput or error-rate thresholds, and rotates accounts. Requires an OpenAI-compatible gateway (default :8326).