Plugins
Parcourez, filtrez et installez des plugins DeepSeek-Harness.
118 plugins trouvés
dsh-lawkb-ui
iambatman1928/dsh-lawkb-ui
Espace de travail de connaissances juridiques : recherche hybride par mots-clés, statistique et vecteurs dans des corpus locaux de lois `.doc`/`.docx`, filtres à facettes, arbres des infractions et causes civiles, éditeur de documents et quatre outils IA : vérification des citations, revue de contrats, analyse et rédaction par IA.
dsh-memos-local
steven-stack-s/dsh-memos-local
Plugin mémoire Reflect2Evolve : mémoire en couches L1/L2/L3, rétropropagation de valeur pondérée par réflexion, induction de politiques entre tâches, cristallisation de skills et récupération à trois niveaux pour OpenClaw, Hermes Agent et DeepSeek Harness.
dsh-lexiforge
hcy7757/dsh-lexiforge
Cadre de packs linguistiques qui réécrit les réponses du modèle : A effectue une réécriture par LLM indépendant ; B injecte la recherche terminologique FTS5 dans cette réécriture ; C applique dictionnaire local et règles regex ; composite exécute une chaîne telle que B→A→C. Inclut une marketplace GitHub, un installateur ZIP vérifiant chemin, taille et type de fichier, ainsi qu’une validation obligatoire de l’avertissement sur les risques.
dsh-project-brain
yj-liuzepeng/dsh-project-brain
Plugin de mémoire et d’intelligence persistantes de projet pour DSH : analyse d’architecture, contexte intersession, TODO et recherche hybride facultative.
docindex
johnxu22786/docindex
Index sémantique local des documents workspace (MD/PDF/DOCX/TXT) : recherche hybride FTS5 BM25 + embeddings locaux, citations avec numéros de ligne et mises à jour incrémentales.
dknowc-dsh
dylanzhangzx/dknowc-dsh
Suite bureautique de confiance pour le travail gouvernemental/entreprise par Beijing Caizhi Technology (深知可信智能) : trois compétences — conseil de confiance (Q&R politiques/réglementations avec marqueurs de citation + HTML de provenance), recherche de confiance (récupération de politiques/standards faisant autorité avec HTML traçable + Markdown propre) et rédaction de documents officiels (brouillon/réécriture/Word/livraison à en-tête) ; toutes les interfaces passent par le MCP de l'atelier de confiance dknowc (auth Bearer), les produits arrivent dans l'espace de travail de la session, la configuration de clé persiste pour les sessions suivantes ; publié sur npm sous dknowc-dsh.
dsh-context-proxy
evilirving/dsh-context-proxy
Récupération de contexte fine à la demande : outils context_query / context_slice / context_grep qui relisent l'historique déjà persisté avec des citations sûres pour le replay.
dsh-pure-search
silentlamb05147/dsh-pure-search
Local document search for DSH: eight kb_* tools that ingest Markdown, TXT, PDF, DOCX, HTML and JSON into workspace- and session-scoped indexes, returning matching passages with path, chapter and line-range citations; BM25 by default with optional dense retrieval, fully offline and host-only.
dsh-continuity
theseus-whale/dsh-continuity
Continuity host core with default-off turn-ping coverage, bounded raw retrieval, and DSH fold/session adapters
dsh-expert-role
yjnmedia/dsh-expert-role
Expert Library (also called Expert Role or Private Think Tank). Turns research material into loadable expert skills: each expert is a folder with SKILL.md, a manifest and references; only its name and one-line description sit in the skill catalog until the model loads it, so a large corpus stays out of the context. Material is organized into eight categories with two-level browsing. Ships two experts (library guide, DSH plugin) that are copied into the library on first start, fill-only and never overwriting yours. 14 tools create experts, move material in, find documents, plan and record research, dispatch steps to child sessions or open a standalone workspace. Retrieval uses a small local embedding model by default, falls back to keyword matching when it is missing, and can be downloaded from the settings panel; the library folder can live on any drive. The gap list shows which questions went unanswered; agreeing to research one sends it to the matching category session, and the result is checked for how many files were added and whether they are registered. A panel shows call history, session activity and each expert's maturity score. It reads and writes files under the expert root; its HTTP routes accept local, host-admitted requests only (`connection.admit`); research and dispatch reuse or create sessions and spend tokens.
dsh-memory-es
xqh0405/dsh-memory-es
DSH memory plugin backed by Elasticsearch: per-user indices with index-level ACL, a shared team knowledge base, Chinese BM25 plus vector retrieval, and a built-in review and audit panel. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
feiyu-memgate (dsh-feiyu-memgate)
n0rmal-114/feiyu-memgate
Long-term memory through the bundled feiyu-memgate gateway, which the plugin starts on 127.0.0.1 (needs Python 3.11 or newer, nothing to pip install): recalls related memories at the start of each user turn and appends them after the user message as a marked data block, gives the model memgate_remember and memgate_search tools, and adds a /memgate command and a settings page where each feature can be switched off. By default memories are written only when the model calls the remember tool. Keyword retrieval over SQLite by default, with no model and no download; an OpenAI-compatible embeddings endpoint or the optional dsh-feiyu-memgate-embed add-on (local CPU embedding models, downloaded on request) adds semantic retrieval. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-weknora-memory
rennimars/dsh-weknora-memory
Layered context engine for DeepSeek Harness: per-kb WeKnora retrieval fused by RRF, recency decay and hot/warm/cold tiering, standing profile cards, fact-conflict surfacing, plus the four WeKnora tools (list / search / read / ask) for pull-on-demand retri
dsh-research-solver
loneleave/dsh-research-solver
Research-style problem solving in four gated stages: record sources by retrieval tier with local before web, turn each shortfall of existing tools into a gap that needs evidence, score candidates against weighted metrics with a deterministic engine, fuse or improve the weak ones, then iterate on measured deltas. It first indexes the whole machine in two layers (what it can run — runtimes, toolchains, package libraries — and what it holds — code, docs, images, video, models), then organizes a directory into human-facing and machine-facing trees.
dsh-Engram
yhprime/dsh-engram
Experience and skill engine with a sidebar console and exp_record / exp_recall / exp_feedback / exp_consolidate / exp_type tools, stored in a local JSON file. Optional Git backup (off until you configure a remote) pushes the library to a remote you choose; GitHub sign-in uses a device code or a token kept in local settings.
socratic-tutor
icefox12138/socratic-tutor
Socratic tutor tools for DSH: cited retrieval, page images, chapter index, session review, embedded console. Teaching behaviour lives in dsh-socratic-persona.
dsh-daughter
han0han0le0ni/dsh-daughter
Five-layer persona (L1–L5), event memory with FTS5 plus Dice retrieval, cognitive filter, skill cards with auto-frozen asset packs, millisecond reflex rules, three-tier safety degradation, a read-only brain star map, and an optional VPet-Simulator MOD bridge.
dsh-elysia-memory
1148462398-hub/dsh-elysia-memory
Elysia's memory plugin for dsh. One shared, human-editable MEMORY.md across every session: two-disk mirror, history snapshots, cross-process write lock; entries tier between the main file and a searchable archive by hit frequency; retrieval is keyword co-occurrence plus BM25. Nine sections (persona, requirements, corrections, lessons, methods, requests, sessions, method library, ingested docs) plus a dedicated self-identity section for a character's own self-cognition, injected above the persona. Ships an opt-in memory pack (packs/elysia: 61,903-char identity + 2,482-char persona, distilled from 1,696 officially-confirmed voice lines and 112,175 dialogue lines) that is off by default, backs up before writing, only touches identity/persona, and can be uninstalled. Also opt-in voice playback through a local GPT-SoVITS engine, a skills library, and a sticker library that sends a fitting sticker at the right moment. On by default: after every reply a bubble with an avatar pops up (voice.bubble: false turns it off), and unless the agent already spoke itself it costs one extra small-model request. Opt-in voice playback needs a local GPT-SoVITS engine (about 27 GB, installed separately, NVIDIA GPU required; the plugin downloads about 200 MB of weights) and is Windows-only; the automatic second-drive mirror is Windows-only too (elsewhere set mirrorPath, otherwise there is no mirror).
dsh-Immunity-memory (memory-plugin)
thebeautifulice/dsh-immunity-memory
Cross-session long-term memory for DSH: eight memory layers, four notebooks, hybrid SQLite FTS5/vector/graph retrieval, agent-driven automatic capture, write lifecycle hooks, optional write audit, project spaces, forgetting and a visual management page. Full FTS5/vector/graph retrieval needs the bundled Go service, which ships only as a Windows x64 prebuilt; on macOS/Linux, build it from source or the plugin falls back to Node SQLite without FTS5 and retrieval degrades.
dsh-elysia
1148462398-hub/dsh-elysia
Elysia's memory plugin for dsh. One shared, human-editable MEMORY.md across every session: two-disk mirror, history snapshots, cross-process write lock; entries tier between the main file and a searchable archive by hit frequency; retrieval is keyword co-occurrence plus BM25. Nine sections (persona, requirements, corrections, lessons, methods, requests, sessions, method library, ingested docs) plus a dedicated self-identity section for a character's own self-cognition, injected above the persona. Ships an opt-in memory pack (packs/elysia: 61,903-char identity + 2,482-char persona, distilled from 1,696 officially-confirmed voice lines and 112,175 dialogue lines — not written by hand, measured) that is off by default, backs up before writing, only touches identity/persona, and can be uninstalled. Also opt-in voice playback through a local GPT-SoVITS engine, a skills library, and a sticker library that sends a fitting sticker at the right moment.
cyber-self
mrlsss/cyber-self
Per-workspace personal knowledge base for DeepSeek Harness: each identity gets an isolated local library — import PDF, Word, Excel, Markdown, text, HTML and images, auto-chunk and embed into SQLite with FTS5 + vector hybrid retrieval, then ask questions in chat with numbered citations back to the source. Local-first, no cloud upload; vector embeddings need a local Ollama (default bge-m3), and without it retrieval degrades to FTS5 keyword search.
DSH-DREAM
baiqieji-lulu/dsh-dream
A durable RAG-enhanced long-term memory layer for LLM agents, featuring holographic memory, state-slot conflict detection, and timeline retrieval. Requires Python 3.10+ and this repository's Python dependencies: create a venv and run pip install -e ".\[dev]" in the checkout before enabling the plugin (the bundled installer is a PowerShell script, i.e. Windows).
dsh-memory-studio
yuankilo/dsh-memory-studio
Mémoire pour DeepSeek Harness avec cinq sections (souvenirs, arbre, profil, graphe, boîte de réception), une politique de capture par règles pour décider quoi garder ou écarter, et une recherche hybride BM25 et vectorielle sur des fragments parents et enfants. Fournit douze outils d’agent qui lisent et écrivent les mêmes fichiers locaux.
dsh-flavor-memory
lishicheng2054/dsh-flavor-memory
Couche mémoire pour le chat de personnages : sépare persona, voix et état relationnel des résumés, et archive chaque message brut pour le retrouver. Fournit aussi un importateur de cartes SillyTavern et une passerelle compatible OpenAI.