Plugins

Quadro completo de issues local-first integrado na GUI web DSH: vistas Kanban / lista / Gantt / workflow / dashboard, chat de IA por tarefa, anexos e etiquetas, atribuição automática de tarefas todo orientada por dsh-routines — os dados residem em SQLite local (`dsh plugin add @ttmouse/dsh-taskboard`).

Monitor local-first de carteira e lista de observação de ações A para DSH: cotações na barra lateral, P&L das posições, adicionar/editar/excluir no navegador e persistência JSON.

Empacotador de configuração do agente para DeepSeek Harness: empacota os ativos locais do agente (skills/sessões/perfis/configurações/memória) em um zip para migração ou compartilhamento, com varredura de privacidade, restauração baseada em diff, gerenciamento de packs e UI de configurações; a memória é enviada como um espelho Markdown somente leitura, não como o banco de dados ativo.

Notas de voz na entrada, respostas faladas na saída: dite áudio que se torna mensagens de usuário (transcrever), faça o agente ler as respostas em voz alta (falar), local-first em ~/.dsh/voice

Um registro de estado pessoal e motor de decisão local-first para dsh: mantém cada byte de entrada exatamente como recebido, com proveniência em nível de linha, argumenta contra suas próprias conclusões gerando refutadores primeiro, aplica a cada fato armazenado seu próprio TTL e informa onde uma decisão não se apoia em nada.

Inteligência de base de código multilíngue para IDEs compatíveis com MCP, a CLI e o DeepSeek Harness: chat, busca, auditoria, refatoração e relatórios prontos para apresentação a partir de código local.

Insights pessoais de uso local-first em Configurações, com mapas de calor de tokens de 1/7/30 dias e um calendário de 30 dias, composição de tokens, mix de modelos e status das chamadas de skills.

Voz full-duplex local-first para DeepSeek Harness, orquestrada por Muxiva

Chamadas de voz iniciadas pelo agente: `offer_call` faz o humano tocar (接听/拒接/稍后再说); as chamadas aceitas são sintetizadas e reproduzidas localmente com CrispASR + Qwen3-TTS (9 vozes, 2 dialetos chineses), e as rejeitadas devolvem a decisão ao agente.

Reserva local de prompts LIFO por sessão, para colocar de lado temporariamente um texto inacabado do composer e restaurá-lo com segurança mais tarde.

A chemistry workbench panel in the DSH web UI. Draw structures on a Ketcher canvas (a script downloads the build; it renders locally in the browser with no backend), then compute on the current molecule with RDKit without calling a model — formula, molecular weight, exact mass, logP, TPSA, hydrogen-bond donors and acceptors, ring counts, Fsp3, stereocentres, Lipinski and Veber rule-by-rule checks, QED, PAINS/BRENK structural alerts and the Murcko scaffold, plus SMARTS substructure matching, fingerprint similarity, format conversion, standardisation and batch clean-up. A retrosynthesis tab talks to a pluggable backend (Retro* by default) over a single JSON-in/JSON-out process, and states what is missing when the backend is not installed instead of inventing a route. The calculations run in this repository's Python package (rdkit), which is installed with pip separately.

Registers the dsh-mol stdio MCP server, built on RDKit with no network access, into a DSH profile. It exposes 12 tools: three-level SMILES validation with human-readable diagnostics and character positions, molecular properties, drug-likeness and structural alerts, structure rendering to PNG/SVG, multi-molecule grids, format conversion (SMILES, InChI, InChIKey, MOL, SDF, formula), standardisation with a per-step change log, deduplication, SMARTS substructure matching, fingerprint similarity, and batch clean-up that reports every rejected row. The patch only registers the server; the tools live in this repository's Python package and must be installed first — the README gives a `pip install` route and a from-source route, and until the package is on PyPI the from-source one is what works.

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

Evidence-governed experience memory for DeepSeek Harness

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

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.

Persistent project intelligence and memory plugin for DSH: architecture analysis, cross-session context, TODOs, and optional hybrid retrieval

Self-tending living memory in one local SQLite file — a nightly patrol dedupes, merges, decays and cross-links entries on its own, with seven-signal RRF hybrid recall (FTS5 + jieba Chinese-first tokenization, optional vector KNN, graph PPR), a typed knowledge graph, conflict detection instead of silent overwrites, and web telemetry panels.

Local-first HTML review and annotation workspace for coding agents: opens an isolated copy of a file in a browser editor, collects text edits, format changes and element/area comments, and returns a durable handoff the agent can claim and resolve.

DeepSeek Harness (Cordis) plugin — bi-temporal VSA memory + cognition engine + BLAKE3 provenance, exposed as a DSH storage+session plugin. End-to-end tested with a real Python subprocess.

Git-native, auditable long-term memory for AI agents

Local-first file conversion: 26 conversions across images, PDF (with OCR and experimental PDF→DOCX), data, audio/video and office docs; 7 tools, all local, no API keys.

Turns completed DeepSeek Harness public-content work into a browser-local visual magazine with explicit updates and reviewed one-article sharing.

See how you have been using AI: `/session-insights` reviews your DSH sessions over time, shows what worked, which problems kept coming back, and what results were actually produced, then creates a retrospective report on your machine.