Plugins

Three-tier memory (personal, project, session) built on the Hy-Memory engine, with relevant memories injected before each step. Ships seven memory tools (search, add, list, get, update, delete, forget), a settings panel with per-tier lists, editing, change history and duplicate cleanup, real token accounting per write, session summaries written by the engine at session end, and a user profile refreshed from recent memories. Memories can be exported to and imported from MemHub. Needs Python 3.11+ once to install the engine, or uv, which fetches 3.12 itself; uninstalling keeps the stored memories.

Reports how much disk each project’s sessions use, archives old sessions into a dated folder, and deletes only after an explicit confirmation token.

Configuration panel for an existing `oneapi` route of the pi-ai provider adapter (declare that route in the llm-pi-ai settings first, with api: openai-completions): edit display name, Base URL, API key and default model, test connectivity per model and sync the model list from the gateway, with six agent tools and an optional left-sidebar panel. Written for a Baidu-internal gateway: the Base URL placeholder and token link point there, so set your own OneAPI-compatible gateway.

Lists RouterAI prompt, completion and cache-read prices per million tokens for the models configured in this profile, highlighting the active one. Requires a model provider whose config key is `routerai`; without it the table shows no data.

Neumorphism skin for the DSH web UI that re-keys 72 design tokens to a cool-grey palette with a steel-blue accent in both light and dark mode, and adds soft shadows to the composer, cards, floating surfaces and session rows.

Skins the DSH Web UI to match the opencode console — theme tokens, sidebar, chat markdown, tables, the composer and the question dialog restyled through CSS — and shows the current workspace's git branch under the composer. It also hides the sidebar brand row and the New session button.

Sidebar token and cost curve for the current conversation plus a local ledger across all sessions: monthly/weekly rollups, per-turn detail, Excel export with print-ready A4 layout, and a live account balance. Reads session logs only, prices every message by its own peak/off-peak timestamp, and drops fork-inherited history so it is never billed twice. Desktop app only, verified on Windows; the live balance needs a signed-in DSH account.

DeepSeek Harness usage meter: a current-session cost status bar, a per-turn cost next to each completed conversation turn with a cache-hit / cache-miss / output breakdown, and a Codex-style statistics page with token KPIs, a 53-week activity heatmap and weekly cell bars, priced with DeepSeek peak/off-peak rates.

Usage and balance dock for the DeepSeek Harness sidebar: today's spend next to a Beijing-time peak/off-peak pricing band, today's tokens and cache hit rate, and a plain balance row that opens a detail panel. The panel lists the balance account, an eight-week activity heatmap where any day can be selected, and that day's tokens, cache hit rate, peak/off-peak cost and per-session breakdown with each session's own composition bar. Usage is read from the local session logs only; the only outbound request is the balance query against the provider base URL already configured in DSH. A heavily rewritten fork of Aisland-SJL/dsh-usage that uses the same plugin id (usage), so install only one of the two.

Sidebar DeepSeek peak/off-peak pricing hint with a Beijing-time countdown, Chinese public holidays and make-up workdays, daily pricing-rule refresh, official top-up offer status, and your account balance converted to input tokens (read with the DeepSeek platform sign-in already stored in DSH).

Estimates recorded DeepSeek model spend per conversation and turn, with a cost-ranked overview. Built-in tariff table covers 2026-09-11 to 2026-12-31.

Imports DeepSeek usage exports (ZIP, CSV, JSON) locally and renders token and cost trends, per-model and per-API-key breakdowns, cache savings, input/output composition and usage spikes. The interface is Chinese only.

Reads local DSH session logs to show real token totals, session count, estimated cost and budget, a 14-day usage timeline, per-session breakdown and CPU monitoring, plus a draggable token/cost status window and a whale-girl who eats rice as tokens are spent.

Shows the DeepSeek account balance (recharge plus bonus) in the DSH composer dock and refreshes it automatically.

Models 64-token cache blocks and calculates per-turn API costs and cache ROI.

Shows ChatGPT, Gemini and Grok Bot remaining usage with reset countdowns plus the DeepSeek balance in a compact card above the sidebar account row; thresholds, refresh interval and per-provider HTTP proxies are configurable. Needs existing sign-ins: Codex CLI login for ChatGPT, an Antigravity token for Gemini, a Cursor user API key (CURSOR_API_KEY) for Grok Bot, and a DeepSeek account signed in inside DSH; a row without its sign-in shows a login hint instead of numbers.

Shows Qwen Token Plan, Z.ai GLM Coding Plan and MiniMax Coding Plan quota usage in three cards under Settings → Models, reusing the configured provider API keys for Z.ai and MiniMax and a dedicated browser-window sign-in for Qwen.

Records token usage per turn into two ledgers, imported history before installation and new events after, and shows exact per-bucket totals, per-model and per-session breakdowns, and day/week/month filters in a sidebar panel.

Microsoft To Do panel: browse lists, add, edit, complete and reopen tasks, and open notes, due date, reminder, recurrence, steps and attachments. Lists can be collected into local groups, and a batch of tasks can be picked into a My Day shortlist. Signs in with the Microsoft device-code flow; the token cache belongs to the upstream microsoft-todo-mcp server, pinned to 0.2.0 and started with npx (so Node.js and npm access are needed) with only an allow-listed environment, while groups and My Day live locally. Today, Overdue, My Day and new due dates and reminders follow the device time zone (override with DSH_TODO_TZONE). Chinese and English UI.

AI news panel for the sidebar: 24-hour picks, recent stories, a top-ten trending board, the daily digest and keyword search, all read from the public AIHOT JSON API. Picks and All filter by six categories; feed cards show category, source, time, heat score, summary and, when AIHOT supplies one, its recommendation note. The Picks, All and Search feeds group stories by Beijing-time day and page ten at a time with cursor endless scroll plus a Load more fallback. Read-only and client-side only, with no API key, no build step and colors taken from the host theme tokens.

Fork of SheepofSheep/dsh-doyourweb that puts the browser on another machine: the MV3 extension dials out to this plugin over TLS, so DSH reads and acts on a remote Chrome or Edge rather than a local one. It also generates ready-paired extension packages for the current configuration, adds tab open and close tools, writes annotation detail to a file instead of pasting it into the chat, and shows a checklist naming which part of a remote setup is misconfigured. Interfaces with no DOM at all are reachable too: canvas games, canvas maps and hand-drawn widgets take coordinate clicks, drags and wheel input that glide, pause and hold like a person's, and the viewport is checked before every action so a stale coordinate is refused rather than clicked blindly. It reuses the same browser-tabs plugin id as the upstream, so do not install both in the same profile. Requires Chrome or Edge 125+ and an unpacked MV3 extension loaded manually on the browser machine; the plugin does not install the extension. With tls: true, trust the generated ca.crt as a root certificate there. The extension gives the model access to the tabs and signed-in sessions of the browser it is paired with. The bridge listens on 127.0.0.1 by default; a non-loopback bind needs remote: true, and the extension pairs with a token confirmed by the user.

Token usage for the DeepSeek Harness web UI: a header chip opens a panel with a 26-week daily heatmap (four blue levels scaled to the busiest day), a per-model bar chart, and totals for all / 30 / 7 days — tokens, sessions, calls, active days, peak hour and top model. Reads local session logs only, no network.

Fork of Yuuz12/dsh-webui-auth adding a deny-by-default allowlist route gate over resources, plugin bundles, /api and WebSocket upgrades; password and OIDC/SSO login with an SSO-only mode; server-side sessions with HttpOnly cookies plus a per-browser session list and selective revocation; an OAuth 2.1 device authorization flow (RFC 8628) for app and CLI access, with independent device sessions that expire only on explicit revocation; and a core session bridge that exchanges the launch cookie on the server without exposing the launch token. It is a fork of Yuuz12/dsh-webui-auth and cannot be installed alongside it — remove the original from the profile's bundle list first.

Appends one short user message before the next step when the model is circling: the same absolute path written three times with no measurement landing in between, the same error episode (tool, target and normalised fingerprint) returning twice, or a write followed by two steps with no measurement — the last one only arms, and the message lands before the next write rather than interrupting reading. A measurement has two states: intent is judged from the tool arguments at call time, and the write streak is cleared only when the result comes back, only for that command directory. A failed test still counts, because it yields the line that is wrong. Hard measurements are `lsp_diagnostics`, `verify`, `run_tests` and `run_test`; `ops_bash`, `bash`, `shell` and `pwsh` count only when the command matches a measurement pattern, so `ls` no longer launders a blind edit streak. Signals fire once per episode, re-arm after a real measurement, and are capped per turn; a successful `present` sleeps the gate until the next write, and subagent sessions are skipped. Generated paths (build output, lock files, logs) are excluded. Error targets are read out of real `file:///` ESM stacks, so two different files never collapse into one episode, and `cd <dir> && cmd` counts as a measurement of that directory rather than its parent. Ships the `stuck-gate` skill at bundled rank 600 (a user-level copy at 400 overrides its wording) plus a read-only observation panel at `/better-debug` reporting firings, sessions covered, the first action after each message across six classes, and how many measurement loops actually closed. The log defaults to `$DSH_HOME/logs/better-debug.log` and is created on first write, so the panel has data right after install. Optional host services are subscribed dynamically, so a host without them still loads the gate. It does not estimate tokens saved, and it does not claim the message caused the change. The panel banner counts only the failures after the most recent load (`log.current`), so one old mount failure no longer reads as "currently disabled". Test suites wait for log conditions instead of fixed delays (test-only change in 0.2.5).