Plugin

Ponte visivo per modelli solo testuali: incolla un'immagine e ottieni prove strutturate in JSON (OCR, layout, semantica).

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

Ponte di ricerca web per agenti solo testuali: interroga il web o X e ottieni prove strutturate in JSON (ricerca, fetch, citazioni).

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 di agenti per la ricerca: controllo degli obiettivi a lungo termine con catene di prove verificabili, pianificazione cron, squadre di esperti multi-agente, memoria di ricerca auto-evolutiva (recupero FTS5 + RRF), spazi di lavoro per progetto e una UI personalizzata per lo spazio di lavoro.

Aggiunge a DSH Web un catalogo di plugin integrato con ricerca, spiegazioni sullo stato e interruttori sicuri per i plugin UI verificati.

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.

Aggiunge ricevute JSONL locali concatenate tramite hash per i risultati degli strumenti e gli eventi di sessione, senza memorizzare prompt, argomenti degli strumenti, testo dei risultati o ID di sessione grezzi.

Sidecar di vision gratuito e ospitato per DeepSeek Harness, con prove di sessione persistenti.

Guardia della disciplina ingegneristica: interroga a fondo i requisiti prima della prima modifica, impone gate di evidenza sui test red/green e verifica la consegna con un avversario biforcato (skill grill-requirements + gate delle policy sugli strumenti)

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 basato sulle prove: sei strumenti in sola lettura (catalogo delle capacità, piani di workflow a stadi, lettore di skill impacchettate, ricerca limitata nella memoria locale, audit delle release del repository, checklist di release) e cinque skill impacchettate — pianifica e verifica, senza mai scrivere da 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.

Scanner locale rispettoso della privacy per i metadati di sessione/workflow di Codex, Claude Code, WorkBuddy e CodeBuddy; conserva prove aggregate e consiglia i preset agente integrati di DSH senza conservare i contenuti, usare la rete o modificare i preset

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.