Plugin

DeepSeek Harness settings-pro plugin: IM bridge (Telegram/WeChat), DeepSeek usage, cross-restart memory, desktop pets, and a vision bridge

DSH plugin: automatic dual-peer Honcho v3 memory, contextual recall, search, reasoning, conclusions, and health diagnostics

Complement to official Creator mode: stage, validate, live-mount via ctx.plugin, score, and solidify or roll back in-memory tool-plugin trials.

Vision plugin for text-only DeepSeek Harness models: native image paste, layered evidence memory and cache, and intent-driven tool selection.

Vision toolkit for text-only DeepSeek: model-invokable `vision` tool, wrapper adapters for deepseek/opencode-go (v4 flash/pro), Antigravity IDE quota (default, flash/pro) / any OpenAI-compatible VLM / Gemini / local Ollama channels, evidence memory with compaction rehydration, content-hash cache, and a bilingual client panel.

Agent config packer for DeepSeek Harness: pack local agent assets (skills/sessions/profiles/settings/memory) into a zip for migration or sharing, with privacy scanning, diff-based restore, pack management, and a settings panel.

Stage-gate governance tools: model-callable gate_open / gate_check / gate_list / gate_close for in-memory, per-session acceptance checks with PASS/BLOCK conclusions.

Long-term memory injected at session start: preferences/facts/summaries/knowledge in global and per-project scopes, budgeted recall via `agent/pre-step`, durable JSON store.

Brings your existing Claude / ChatGPT history into DSH: instant zero-token import of the memories.json inside a Claude export, local Claude Code transcripts with no export needed, and conversations distilled through the model you already configured in DSH. Every memory carries verbatim evidence checked against the source by code — a paraphrase is dropped and counted, and evidence found only in the assistant turns is always routed to review rather than stored.

Conversation history recall for DSH: three-layer (literal/fuzzy/semantic) retrieval over every past session's original text, fully local & offline — AI never forgets what you told it. One-command install via `dsh.bundle.patch`, semantic layer runs in a worker thread.

Cross-session plaintext memory: deterministic BM25 keyword recall (no embeddings), memory_save/list/search/confirm/forget tools behind a human-confirm gate, and global + project-scoped JSON stores that follow your git repo.

Layered memory pipeline for DSH: auto-distills conversations into atomic facts, scene summaries and a persona profile (L0–L3), with hybrid BM25 + vector retrieval, chat/work family separation, and context injection before each model step.

Automatic, local-first cross-session memory for DeepSeek Harness: layered Event/Element cards, evidence-gated recall, and expansion back to original turns and tool results.

Sidebar system monitor for the DSH Web UI: live host overview (CPU/memory/network/disk), process list, and Docker container status, all read-only.

Displays real-time CPU and memory usage for the machine running the DSH Web server.

Memoria di passaggio di consegne autonoma per directory di lavoro e branch git: registra i turni, li condensa in Markdown conciso e inietta il risultato nelle sessioni future da ~/.agent/agent-handoff, compatibile byte per byte con pi-handoff

Wiki Markdown locale come memoria a lungo termine per DeepSeek Harness — portato da llmwiki

Gruppo di plugin ProactiveAgent × DeepSeek Harness: memoria proattiva + suggerimenti proattivi integrati in DSH (bundle aggregato, installazione con un clic tramite dsh plugin add)

Memoria di persona persistente a lungo termine per DeepSeek Harness: archiviazione in MEMORY.md/USER.md, strumenti memory + memory_search, iniezione del contesto per richiesta e scansione dei segreti. Portato nello spirito da pi-hermes-memory

Un plugin per DeepSeek Harness che trasforma la sincronizzazione git di anywhere-claude-mem in un peer DSH: recupera la memoria cross-macchina all'avvio della sessione e invia nuovi prompt/osservazioni non appena arrivano nel worker claude-mem

Un plugin di stato per dsh con una metà lato host e una lato browser: stato di salute a runtime dell'harness (processo, listener, presenza della chiave API, memoria, uptime, inventario dei plugin) come JSON più avvisi SSE inviati dal server, mostrati come badge nell'intestazione con un pannello espanso nella Web UI

Plugin per DeepSeek Harness: client Nocturne Memory — memoria a lungo termine automatizzata (boot/read/search/create/update) basata sul tuo server Nocturne MCP

Backend di memoria vettoriale + a grafo: strumenti observe/remember/search/recall verso un server memoria locale, che fonde il richiamo semantico HNSW, la ricerca per parole chiave FTS5 e i segnali del knowledge graph tramite ranking RRF, con persistenza automatica a fine turno e isolamento dei namespace per agente

Deposito di memoria cross-sessione: strumenti remember / recall / forget, iniezione nel prompt per turno e un browser delle voci nella pagina delle impostazioni