Plugin
Sfoglia, filtra e installa i plugin di DeepSeek-Harness.
69 plugin trovati
dsh-workbench-shell
lucky01222/dsh-workbench-shell
Rail di navigazione compatto da 56px per DSH Web UI, con elenco conversazioni separato e controllo per comprimere la sidebar. Nasconde anche i modelli di embedding, rerank e generazione immagini/video dal menu modelli della chat e da `/model`.
dsh-wsl-vecmem
173787247/dsh-wsl-vecmem
Piccola memoria vettoriale locale con embedding Ollama in ~/.dsh/vecmem e namespace per workspace; nota IM facoltativa tramite vecmemOnReply.
docindex
johnxu22786/docindex
Indice semantico locale dei documenti workspace (MD/PDF/DOCX/TXT): ricerca ibrida FTS5 BM25 + embedding locali, citazioni con numeri di riga e aggiornamenti incrementali.
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-lcm
zy-xyz/dsh-lcm
Lossless context compaction: an LLM summarizes a leaf of compacted events and replaces it with one checkpoint node, nothing is deleted, so lcm_search still matches text a checkpoint summarized and lcm_expand restores any event by seq. Summaries condense at fanin 4, a threshold crossing sweeps several leaves under two clocks, and an idle pass resumes a sweep that ran out of budget. Optional semantic recall ranks events against any OpenAI-compatible embedding endpoint, with a /lcm-embed backfill command and status. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-session-media
ok541151/dsh-session-media
Session-archive layer for DSH. It injects one per-workspace Markdown file into the system prompt on every turn, searches past session transcripts with AND keywords, an optional time window and a workspace filter, and recovers the images and documents those past sessions carried by returning their original local paths or copying them to a chosen directory. It also reports index health: version, entry count, cache usage, frequent sessions and sessions stored in an archive format it does not recognise. Keyword search only, no embedding service.
dsh-team-workbench
narkco-kang/dsh-team-workbench
A named-agent-team chat workbench for DSH: per-member model routes with fallback and 3D mascot avatars; private and group chats with mention relay and bounded parallel lanes; a whole department as one agent whose lead dispatches sub-agents that run in parallel on their own models before the lead synthesizes; record search with hit highlighting and today/yesterday/earlier buckets; a four-layer memory system (raw chats → atomic facts → scene summary → user persona) recalled by hybrid BM25 + embedding RRF; plus an avatar library and local/cloud speech input. Hybrid recall needs an embedding endpoint (default: local Ollama qwen3-embedding:0.6b; otherwise BM25 only); speech input needs a local jianchang512/stt service or a cloud ASR key, otherwise it falls back to the browser speech API.
dsh-arxiv-inspiration
lxion0553/dsh-arxiv-inspiration
arXiv paper survey assistant with a settings-page UI, a local knowledge base, a feedback loop, keyword search plus optional local-embedding semantic search, and per-paper deep-read notes. Requires a configured DSH LLM provider; semantic search and full-text deep read need an optional Python environment (pymupdf + fastembed), otherwise they fall back to keyword search or are skipped.
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-obsidian-memory
aoyamabf-max/dsh-obsidian-memory
Stores the agent's long-term memory as plain Markdown in an Obsidian vault — every memory is a .md file with YAML frontmatter that Obsidian indexes natively, so you can read, edit, link and back up it with tools you already use. Nothing is locked in a database. Ships a sidebar panel (tag filter, sort by recency or importance, edit in place), 7 agent tools, three-tier token-budgeted recall, BM25 ranking (no embeddings, no API key, works offline, CJK bigram tokenization), importance decay with archiving (moved to .archive/, never deleted), and optional GitHub Contents API sync. A note containing a secret is refused rather than redacted, because a redacted memory reads as complete while the important part is gone. Zero runtime dependencies; everything comes from the DSH host.
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.
BiliMemory
binbin-qaq/bilimemory
Collega DSH a un backend BiliMemory locale per ricerca, raccolta, stato e accesso Bilibili; verifica la memoria condivisa A-Memorix, il collegamento QQ, allowlist e riavvio del watcher QQ. L’installer Windows con un clic installa/ripara MaiBot A-Memorix se manca e configura local-bge-small-zh, embedding e memoria condivisa; `install-memory.cmd` ripara solo la memoria. Richiede Windows, DSH Desktop 0.2.1-rc.2+, Node.js 22.19+, Python 3.12, Playwright/Edge, FFmpeg, API BiliMemory su `127.0.0.1:8765`, servizio embedding locale su `127.0.0.1:11435`, login Bilibili e MaiBot/NapCat per QQ. Voce, RVC e funzione cover sono escluse.
dsh-qqnt-chat-export
ariyflow/dsh-qqnt-chat-export
Legge NTQQ locale (QQ 9.9.x) su Windows/Linux ed esporta chat di gruppo/private in txt/csv/json/md/html/sqlite. 16 strumenti: qqnt_status, qqnt_doctor, qqnt_extract_key, qqnt_index, qqnt_list_groups, qqnt_list_chats, qqnt_search, qqnt_stats, qqnt_export_group, qqnt_export_chat, qqnt_export_batch, qqnt_jobs, qqnt_media, qqnt_storage, qqnt_ask, qqnt_recall (rifiuta l’ambiguità; pulizia solo su lista autorizzata). 127.0.0.1:46728: indice SQLite incrementale, 6 viste, task, colonna singola su schermi stretti, mittenti oscurati, media raggruppati, divisione giornaliera, preset, ZIP AES-256 con password. OCR/voce/embedding si installano su richiesta nel virtualenv del plugin. Richiede python3/sqlcipher3; Impostazioni può creare il virtualenv privato. Chiave DB dal client QQ attivo e autenticato.
dsh-mem0
0junze0/dsh-mem0
Memoria a lungo termine basata su mem0 e archivio Chroma locale: inserisce profilo utente e fatti recuperati nel system prompt e acquisisce dati al termine della sessione. Un processo notturno elimina duplicati, unisce parafrasi e risolve contraddizioni; un grafo persistente degli argomenti viene scritto in schede Markdown. Esportazione periodica in un repository Git e interfaccia memoria a pagina intera con ricerca, unione in blocco, snapshot e annullamento. Prima dell’uso servono configurazione manuale di un Python venv e chiavi API LLM ed embedding.
dsh-lattice
topkie/dsh-lattice
Memoria locale per DeepSeek Harness: archivia per argomento e collega voci correlate; il richiamo ordina per similarità degli embedding, usando le parole se manca un modello. Dati in SQLite locale.
dsh-coderag
vermilionpasvikin/dsh-coderag
Motore MCP di code retrieval SQLite FTS5/BM25: code_search/code_outline/code_index/index_status. Bigrammi CJK, chunk tree-sitter consapevoli delle dichiarazioni, reindicizzazione incrementale, filtro segreti a tre livelli. Query cinesi trovano codice inglese; niente vector store/embedding per default. Richiede engine locale Python 3.10–3.12 via scripts/install.sh e CODERAG_ROOT nel profile patch.
dsh-anima-rag
vv5v5/dsh-anima-rag
Memoria vettoriale in stile Anima per DSH: inserisce a ogni turno riepiloghi storici recuperati nel system prompt e offre lo strumento di ricerca semantica `anima_query`; lo store vettoriale è isolato per partita. Le richieste di embedding SiliconFlow hanno forma di array; timeout ed errori del provider sono mostrati come note esplicite e classificate nell’area di iniezione, mai in silenzio.
dsh-memento
janpauldahlke/dsh-memento
Memoria a file limitati per agenti locali: archivio `ME.md` e `MEMORY.md` per progetto, iniezione stabile in cache, posta in arrivo a righe di testo semplice e barra laterale Memory. Senza embedding o chiamate LLM.
dsh-memory
navid-kianfar/dsh-memory
Memoria persistente, ricercabile e per progetto per DeepSeek Harness: decisioni, regole e contesto sprint in un file DuckDB interrogabile; regole applicate a ogni richiesta al modello e UI di gestione completa nel Web Client.
dsh-mnemosyne-memory
fjzzwxp/dsh-mnemosyne-memory
Plugin di memoria permanente per DSH con ricerca vettoriale, riflessione LLM e pagine di conoscenza.
dsh-code-intel
lonelymoon87/dsh-code-intel
Indicizza i simboli del workspace con Tree-sitter e offre una ricerca del codice lessicale o, opzionalmente, assistita da embedding