Плагины

Reflect2Evolve memory plugin: layered L1/L2/L3 memory, reflection-weighted value backprop, cross-task policy induction, skill crystallization, and three-tier retrieval for OpenClaw, Hermes Agent, and DeepSeek Harness.

TypeSafe Jev (решающая модель System One) для DeepSeek Harness, от начала до конца: jev_decision (choice/score/noul, параллельно, типизированные ответы + уверенность), карточка Settings > Plugins для API-ключа и переключателей, встроенные представления инструментов, показывающие каждое решение в диалоге (ответ, уверенность, задержка, стоимость), авто-защита (детерминированные проверки + проверки риска и циклов от Jev), локальный дашборд /jev и онлайн-бенчмарк верификации (96.3% на 27 размеченных вопросах, медиана ~283 мс на jev-latest, 2026-09-21). Честность по замыслу: только реальный API, без mock-заглушек.

Local SQLite long-term memory with CJK-aware search, BM25 and character n-gram cosine reranking, deduplication, and lifecycle management.

Adds a sidebar panel to the DeepSeek Harness web UI that reports token usage and cost straight from DeepSeek's own usage API (today's spend, 7/30-day trends, today's hourly split, a history table, cost breakdown, peak/off-peak tier pricing), plus per-session detail from local logs. Zero-config: it reads the browser sign-in for the official figures, and falls back to local session logs with the source labelled.

DSH settings section for managing a local Sirchmunk knowledge backend: graph inspection, cluster management, audit history, runtime metrics, and privacy controls.

Bridges Feishu, WeCom, DingTalk, QQ, Slack, Discord, Telegram and Mattermost into dsh agents (outbound WS/Stream/Gateway/long-poll/webhook), with im_status, optional local Whisper ASR, plain-text outbound for QQ/DingTalk/Telegram/Mattermost, and env CSV allowlists (DSH_IM_*_ALLOWED_USER_IDS). Empty allowedUserIds means EVERYONE can drive your agent — set a whitelist before exposing a bot.

Pool AI provider accounts per platform and route them through a local loopback proxy that bridges the OpenAI, OpenAI-Responses, Anthropic and Gemini protocols, then write the proxy into Codex, Claude Code, Gemini CLI, Grok, OpenCode, OpenClaw and Hermes config files with snapshot-and-rollback safe writes; registers no agent tools.

Ren'Py galgame production workbench: a host-side project service (write gateway plus git snapshots, a dialogue/scene dialect parser, derived progress, human-only review stamps, pinned-SDK validation and playtest, local publish) behind one seam, driven by an embedded web panel and agent tools.

A right-sidebar Git panel in the IDEA style — local changes with per-file checkbox commits, a commit tree with per-commit details, branch, remote and stash management, push with a credential fallback, all driven by the plain git CLI.

English word bank for one or more children, built for DSH 0.2 and newer (0.2.0-rc.1 and 0.2.0-rc.2 verified, including the desktop shell; 0.1.7 through 0.2.x all work). 1.10 added pronunciation: in the memory cards and in the online quiz every word and every example sentence has a speaker button that reads it aloud with the built-in Windows voice - offline, with no network call and no model call - and the whole batch of audio is pre-rendered in the background whenever cards or an exam are generated, so a click starts instantly. 1.11 adds: pick words in bulk straight from the library (10 at a time, top-down, up to 50 selected, with a live counter); turn the words a child got wrong in a quiz into a one-click review set - an online card page that speaks plus a printable PDF; and every card example sentence now carries its Chinese translation underneath. Words marked on textbook or workbook photos (highlighter, red pen) are found by their marks, then translated and stored in a local SQLite bank with an occurrence count; the clipboard picker, the photo route and dictation all land in the same bank. High-frequency words surface by count, three correct answers in a row flag a word as learned, and any selection prints as a memory card set (a word split into chunks, real IPA per chunk, a grade-7 example sentence, a mnemonic hook, an A4 sheet of eight) in HTML, PDF or Word, with a print-and-answer exam page whose four options are set against each other for meaning. On 0.1.5 the settings panel does not appear - install dsh-word-vault@1.0.2 instead.

Global token totals across every local DSH conversation, de-duplicated by message id, with custom date ranges and per-provider monthly quota tracking.

Adapt ERP: learn your ERP through the browser and build private local knowledge in DeepSeek Harness

Read web novels inside the DSH web GUI: import legado book sources, search across them, keep a bookshelf with reading progress, read in one continuous scroll, import local TXT and EPUB books, and let agent tools reach the same sources, shelf and text.

Intent fitting for DSH: the agent predicts several directions first, asks a batch of clarifying questions each round, narrows the distribution until one converges, then proposes it for your confirmation. Bottom-right floating panel, local JSONL archive, a

Spanish (es) language pack for the DeepSeek Harness Web UI — a community DSH client plugin adding Español to Settings → General → Language.

Evidence-governed experience memory for DeepSeek Harness

Local-first voice conversations for DSH, with local speech recognition and synthesis and optional external providers.

Built-in browser control for dsh (DeepSeek Harness): lets the AI agent open pages, read content, click, type, scroll and take screenshots in a real local browser (Edge/Chrome via the Chrome DevTools Protocol). Includes a docked live browser pane (CDP scre

FreeDSH — free-first multi-model routing, safe core updates and pt-BR/Windows support for DeepSeek Harness. Installable as a DSH bundle (dsh plugin add). Unofficial project.

DeepSeek Harness browser-control tools backed by the pi-control-chrome local Bridge

Live token cost for every chat in the DSH Web UI: the chat, its subagents and the whole session tree, priced from a bundled models.dev snapshot of seven providers and 139 priced models, with cache read and write rates wherever the provider publishes them and DeepSeek from its own peak and off-peak table. Every finished answer carries its own price in the transcript, and a chat that is not currently open is priced from the log instead of disappearing. Spend is costed per interval from an append-only JSONL ledger in the project folder, so logged work keeps the tariff it was billed at. On top of it: budget-aware work plans packed against a money limit, routing scenarios that show which models are worth connecting, a generated plan document in English, Chinese or Russian, and a warning when spend belongs to no plan unit.

Beginner panel for DeepSeek Harness: routes a plain-language request into ready-to-use plans (prompt variants, matching skills, advanced moves) with a local keyword engine and fills the chosen plan into a new session in one click.

Zhihu (知乎) for DeepSeek Harness: wraps the local pyzhihu-cli as 18 zhihu_* tools — 14 read-only (search, hot list, question, answer, user, feed, topic, notifications, collections) plus 4 publishing tools that are not registered until readOnly is turned off — with a web panel in the sidebar for login, config and lookups.

WebDAV server: turns a shared directory into a WebDAV service that Windows, macOS and Linux can mount as a local disk, with token authentication, optional read-only mode, configurable directory/port/token, and per-platform mounting guides built into the settings page.