Plugins

Puente de visión para modelos de solo texto: pega una imagen y obtén evidencia JSON estructurada (OCR, diseño, semántica).

Software-engineering method pack for coding agents, with skills for baseline-first planning, systematic debugging, prompt hygiene, verification before completion, and repair/retirement tracking.

Puente de búsqueda web para agentes de solo texto: pregunta a la web o a X y obtén evidencia JSON estructurada (búsqueda, obtención, citas).

Cleans AI traces from Russian text: finds chatbot copy-paste artefacts (ChatGPT, Gemini, Grok, Perplexity, DeepSeek) and rewrites the text into natural prose on request; 39 regex markers with an evidence registry, offline, text-only bundle.

Deep-read books and articles in five modes (quick, deep, knowledge map, Feynman, full book) with claim-evidence-data reports, Mermaid/XMind mindmaps, batch comparison, budget preflight, transparent background-job progress, and MD/HTML exports from URLs, files, or pasted text.

Academic writing guard (EN/ZH bilingual): removes AI-style defensive writing, protects scientific evidence (numbers, citations, claim strength, null findings, scope) during polishing, and calibrates writing toward a target journal (Journal Profile + Journal Fit). Deterministic local regex/statistics, zero network/LLM; writing_rules / writing_audit / writing_style_profile / writing_journal_profile with auto-audit on paper writes.

Free vision bridge and image generation for text-only models: paste-image reading, GLM-4V-Flash and Gemini engine failover, ModLens-style structured evidence, and a seeded free vision model route.

Vision for text-only DeepSeek via Doubao Web by default (zero-cost, no API key — drives your logged-in Chrome through a Windows CDP bridge), with Antigravity IDE quota (flash/pro) or Gemini fallback; auto detail escalation, vision evidence memory with compaction rehydration, content-hash cache, and a bilingual client panel.

Suite de agentes de investigación: control de objetivos a largo plazo con cadenas de evidencia auditables, programación cron, equipos multiagente de expertos, memoria de investigación autoevolutiva (FTS5 + RRF) y una UI de espacio de trabajo personalizada.

Añade un catálogo de plugins integrado a DSH Web con búsqueda, explicaciones de estado e interruptores seguros para plugins de UI auditados.

Let agents search, read, and cite your local Zotero library: find papers, view notes and annotations, pull evidence by question, open the source document, and generate citations.

Technical-preview local graph memory for DSH and Codex: recalls owner-global and current-project evidence before each turn, writes USER and ASSISTANT records separately, and preserves project, session, actor, and source provenance for a visual atlas and cited knowledge pages.

Always-on dependency security for DSH plugins: tracks exact installed paths, OSV vulnerabilities, npm releases, and breaking-change signals, then routes project evidence to a DSH Agent.

Añade recibos JSONL locales encadenados por hash para los resultados de herramientas y los eventos de sesión, sin almacenar prompts, argumentos de herramientas, texto de resultados ni IDs de sesión en bruto.

Sidecar de visión gratuito y alojado para DeepSeek Harness, con evidencia de sesión duradera

Guardián de disciplina de ingeniería: cuestiona a fondo los requisitos antes de la primera edición, exige evidencia de pruebas red/green, y audita la entrega con un adversario bifurcado (skill grill-requirements + políticas de herramientas).

Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness with source-preserving evidence.

Evidence-first guard: warns the agent when it claims success without a matching tool-execution record in recent context.

Evidence-bound negative-knowledge ledger: persists disproven paths (command_failed, file_missing) with their outcome and precondition evidence, then warns or blocks repeat attempts until the evidence changes.

Kit operativo basado en evidencias: seis herramientas de solo lectura (capacidades, planes por etapas, lector de skills, búsqueda en memoria local, auditoría de releases, checklist) y cinco skills empaquetadas; solo planifica y audita, nunca escribe en remoto.

Evidence-first self-evolution controller: bounded Cordis candidate generation, one-shot real-Loader admission, Harbor evaluation, and a crash-resumable journaled lineage.

Adds persistent execution contracts, recursive work graphs, critical clarification, and evidence gates for long or underspecified Harness tasks.

Escáner local respetuoso con la privacidad para metadatos de sesión/flujo de trabajo de Codex, Claude Code, WorkBuddy y CodeBuddy; conserva evidencia agregada y recomienda preajustes de agente integrados en DSH sin retener contenido, sin usar la red y sin modificar los preajustes.

Falsification-driven correction loop for agent sessions: risky work commits an evidence-checkable claim first, deterministic gates verify it, falsified claims force mutually exclusive replacement hypotheses with discriminating experiments, and every event lands in an append-only evidence ledger.