Plugin
Sfoglia, filtra e installa i plugin di DeepSeek-Harness.
126 plugin trovati
dsh-memory-nebula-bridge
2930136787xy-tech/dsh-memory-nebula-bridge
Bridges a memory-nebula store into DSH: a panel inside the Harness UI to search, edit, pin and forget memories, plus three agent tools to check, search and revise them.
dsh-memory-fish
github-yxm-hub/dsh-memory-fish
Context-budgeted local memory for DeepSeek Harness: fixed ~600-token cache-friendly injection (session/daily snapshots), three-stage sleep consolidation, spaced repetition, temporal validity, subagent-driven L0 mental-model rewrite, typed memories (fact/s
dsh-memory-archiver
imaused/dsh-memory-archiver
Approval-free memory archiving for DeepSeek Harness: writes Markdown memory files without approval prompts, backs the old file up before any overwrite, marks a revised conclusion as status: superseded in one call, and prunes old backups after 30 days by default (optional size cap). The writable scope is hard-limited to configured memory roots (default ~/.dsh/memory). Companion to dsh-kb-lite, which indexes these files and down-weights superseded ones. Host-only, no npm dependencies; requires Node.js 18+.
dsh-memory-cloud
faruzancn/dsh-memory-cloud
Visualizes all DSH session memories as an interactive 3D nebula, with a neuron-signal skin, memory-scaled clusters, zoom-driven detail levels and a live write/read activity stream over SSE.
dsh-whale-memory (dsh-slow-wave)
xiaocanglan-hub/dsh-whale-memory
What it does while she sleeps, in one card. Two things: (1) tidy the element memory — merge synonyms only when the model agrees, trim descriptions, prune weak links, propose analogies for the user to confirm, with a backup before every write and a 15%-of-library cap per pass; (2) dream — stitch her own past experiences (plus props from the element memory) into a short 3–6 sentence story, leave one line on her desk as a note labelled "this is a dream, not something that happened". The dream lives in its own file and never enters her memory or her personality prompt. Requires @ssamurias/dsh-fish for her event stream and dsh-memory-brain for the element library; model-approved merges and dreams need a local Ollama model (or a paid API key).
dsh-whale-memory (dsh-memory-brain)
xiaocanglan-hub/dsh-whale-memory
Object memory for DSH: each object is broken into fourteen kinds of smallest elements (shape, material, state, part, function...), observed links are stored apart from inferred ones, and analogies stay as questions until the user answers.
dsh-memory-v2
yanlrx/dsh-memory-v2
Rui Xi's Memory (dsh-memory-v2) — a local long-term memory plugin for DeepSeek Harness: four memory collections (semantic / conclusion / profile / temporary), per-day scene archives, two-phase consolidation and literal trace. When structured recall finds nothing, it falls back to searching the daily scene archive: time-window first (yesterday / last week / N days ago / dates), then a 2/7/30/180-day tiered sweep, with line-numbered citations. All data stays in the local DSH directory; semantic recall, diagnostic logs and the sensitive debug route are off by default.
dsh-memory-engine
jiudouliang/dsh-memory-engine
DSH 本地记忆插件:自动记忆、遗忘曲线、关键词关联、可检索可编辑,数据留在本机。
dsh-memory-router
dcd887/dsh-memory-router
Intercepts DSH tool results before the model reads them: dedupe cache for repeated calls, a declarative decision graph that replaces large outputs with structured digests, an injection gate, and an honest token ledger that includes a negative-return account for over-compression. Measured 1400-1600 tokens saved per hit; the cumulative ledger is currently negative and the README says why, including that it cannot skip model turns.
dsh-memory-chain
raoain/dsh-memory-chain
Layered memory for AI agents: five verbs (wake/work/pit/tomb/close), core layer read every time, archive on demand. Plain markdown, four pages created on first run; survives restarts, model swaps and plugin removal.
dsh-memory-graph
ilaomianyang/dsh-memory-graph
Long-term associative memory for DeepSeek Harness: a local plain-text vault of raw episodes, typed memory cards and entity pages, configured from 设置 → 记忆图谱, and a Memory tab inside a conversation that draws what that session remembered. No build step; the
dsh-memory
ascrm/dsh-memory
Local-first, file-backed memory plugin for DeepSeek Harness: Markdown memories, verified trust, per-turn recall, and optional SQLite FTS5.
dsh-memory-hub
zhiwuli0228/dsh-memory-hub
Local-first, file-native long-term memory for DSH with per-turn preflight, compact context injection, citations, human-approved writes, manual consolidation, nightly report-only maintenance, and a Web panel that is read-only for knowledge while allowing workspace-config edits.
dsh-memory-band
13576751971/dsh-memory-band
Local three-band memory for DeepSeek Harness: a 24h protection band, query recall and scene replay, injected into sessions without embedding or model calls.
dsh-memory-studio
yuankilo/dsh-memory-studio
Memoria per DeepSeek Harness con cinque sezioni (ricordi, albero, profilo, grafo, posta in arrivo), politica di acquisizione basata su regole per decidere cosa conservare o scartare e recupero ibrido BM25 più vettori su blocchi padre e figlio. Include dodici strumenti agente che leggono e scrivono gli stessi file locali.
dsh-memory-github
administrator016/dsh-memory-github
Memoria tra sessioni per DeepSeek Harness: archivio locale predefinito, sincronizzazione facoltativa con GitHub tramite git e ruoli primary/child per configurazioni multi-dispositivo.
dsh-memory-tide
xhszdhm/dsh-memory-tide
Mantiene note a lungo termine e diari giornalieri per workspace in un archivio hot/cold, con indice per ogni livello e riequilibrio quotidiano. Lettura e scrittura tramite sette strumenti `memory_*`, con impostazioni per workspace.
dsh-memory-tiers
1129742588/dsh-memory-tiers
Plugin di memoria a sei livelli che cattura ogni turno, inserisce un blocco stabile come user snapshot e compatta la cronologia del host in un solo placeholder senza chiamare un modello.
dsh-memory
2424830124/dsh-memory
dsh-memory
kagurazaka135/dsh-memory
Memoria a livelli tra sessioni in YAML semplice: i fatti mantengono la cronologia delle versioni, un briefing viene iniettato all’avvio e un processo notturno consolida e divide per argomento oltre una soglia. Nessuna dipendenza runtime, funziona anche nell’app Android dsh (verificato).
dsh-memory-doctor
feely0208/dsh-memory-doctor
深鲸记忆: memoria attiva tra sessioni (inietta MEMORY/USER a ogni turno e lettura/scrittura tramite lo strumento memory), controllo della memoria, snellimento/archivio, pacchetti di memoria, report diagnostico e documenti in sola lettura. Testo locale semplice, zero dipendenze, nessun upload.
dsh-memory-kit
xieddenv/dsh-memory-kit
Offre all’agente DSH cinque livelli di memoria persistente in file Markdown semplici: persona, regole di stile, diario, archivio Session e attività aperte. Ricostruisce una sezione del system prompt entro un minuto da una modifica; aggiunge tre strumenti (`memory_read`, `memory_write`, `memory_search`) e un importer per migrare una directory di memoria esistente.
dsh-memory-system-prompt
mcjf28/dsh-memory-system-prompt
Memoria globale: file letti e scritti attivamente dall’IA. Un indice viene iniettato prima di ogni turno senza occupare contesto; il contenuto si espande solo quando serve. Disattivabile per la conversazione corrente.
dsh-memory-guard
zeroed-07/dsh-memory-guard
Protezione memoria solo locale per DeepSeek Harness: monitora heap Host e log di sessione, intercetta argomenti tool troppo grandi e offre pulizia delle sessioni in dry-run per default.