플러그인
DeepSeek-Harness 플러그인을 찾아보고, 필터링하고, 설치하세요.
플러그인 59개 찾음
dsh-memoria
jiayan-xu/dsh-memoria
벡터 + 그래프 메모리 백엔드: 로컬 memoria 서버를 대상으로 하는 observe/remember/search/recall 도구, HNSW 시맨틱 회상·FTS5 키워드 검색·지식 그래프 신호를 RRF 랭킹으로 융합, 턴 종료 시 자동 저장과 에이전트별 네임스페이스 격리 지원
dsh-context-toolkit
chimneyq/dsh-context-toolkit
대량 출력을 대화에 남기지 않습니다. `ctk_execute`, `ctk_execute_file`, `ctk_batch_execute`는 child process에서 코드를 실행하고 결론만 반환합니다. `ctk_index`/`ctk_search`는 긴 자료를 `node:sqlite` 기반 로컬 FTS5 지식 베이스에 저장/검색합니다. routing gate는 실행 전 `curl`/`wget`을 거부합니다. `ctk_stats`, `ctk_doctor`, 실시간 context 점유 panel 설정이 포함되며 타사 runtime 의존성은 없습니다.
dsh-kb-sieve
omdsh-dev/dsh-kb-sieve
md/txt/docx/pdf로부터 감사 가능한 KB 팩(SQLite FTS5)을 구축하며, 결정적 검색과 원문 읽기 지원
dsh-memory-gate
git121995/dsh-memory-gate
CBDC 권한 게이팅이 적용된 제한적 로컬 메모리: SQLite + FTS5 클레임, 설명 가능한 use/verify/ignore 판단이 포함된 범위 기반 회상과 전체 감사 추적, /memory 명령어, 호출당 최대 3개 클레임/1200자 삽입, 추가 모델 호출 없음
dsh-tidal-memory
wjpgkz/dsh-tidal-memory
Workspace-shared L0-L3 SQLite memory for DeepSeek Harness: FTS5 plus optional local embeddings, evidence-gated recall with source and revision provenance, two-hop source-graph expansion, scene timelines, and private journals kept as Markdown files bound to one main session.
dsh-deepmemory
emo-bird/dsh-deepmemory
Cross-session long-term memory for DSH — facts, verbatim episodes and a daily diary in one local SQLite file, plus a sidebar console and per-session switches.
dsh-knowledge
avenyq/dsh-knowledge
Sidebar knowledge base for DSH: indexes local Obsidian vaults and project folders into SQLite FTS5, re-indexes file changes automatically, shows source snippets while you type, and lets the agent answer with numbered citations that open the exact source file and line. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-memory
rosesssss66/dsh-memory
Local long-term memory for DSH: extracts preferences and project facts from sessions, injects the most relevant ones before each turn using local SQLite FTS5 search, and supersedes outdated facts. Requires Node 24+; the offline self-evolution loop needs an OpenAI-compatible LLM endpoint and API key.
alice-memory-llm
cycocyco/alice-memory-llm
Long-term memory for DSH where an LLM decides what to keep: turns pool while the session is idle, then the main chat model distills them into one-line entries in a single batched call; vector dedup runs before insert, so near-duplicates and saturated topics are dropped; recall uses hybrid vector plus FTS5 search over tiered hot, warm and cold storage; ships remember, recall, forget and prune tools. Zero dependencies, Node only.
alice-memory
cycocyco/alice-memory
Long-term memory for DSH: rule gates capture durable facts from conversation turns into a single SQLite database with tiered hot, warm and cold storage; recall injects hybrid vector plus FTS5 hits into the prompt each turn; ships remember, recall, forget and cold-memory prune tools. Zero dependencies, Node only.
dsh-memory-vault
xying-lm/dsh-memory-vault
DSH용 디스크 기반 장기 메모리입니다. 모든 대화 turn을 SQLite FTS5 vault에 저장하고 turn별 문자 예산 안에서 관련 과거 turn을 새 session에 주입합니다. session을 재개 가능한 대화 파일로 묶고 검색, 페이지 이동, 용량을 보는 Web panel을 제공합니다.
dsh-memory-fortress
linshuangb347/dsh-memory-fortress
DeepSeek Harness용 Memory Fortress입니다. 5개 트랙 계층형 메모리, 자기 진화, 지식 그래프(SQLite+FTS5), 상태 배지를 제공합니다. 로컬 메모리 요새: 다섯 트랙 메모리·자기 진화·지식 그래프·상태등.
dsh-lexiforge
hcy7757/dsh-lexiforge
언어 팩 프레임워크로 모델 응답을 다시 씁니다. A는 독립 LLM 재작성, B는 FTS5 용어 검색을 재작성에 주입, C는 로컬 사전과 정규식 규칙 적용이며 composite는 B→A→C 같은 파이프라인을 실행합니다. GitHub 팩 마켓플레이스, 경로·크기·파일 형식을 검사하는 ZIP 설치 프로그램, 필수 위험 고지 확인이 포함됩니다.
dsh-ca-ref
ansonfishing/dsh-ca-ref
DSH용 Clean Architecture 참고 라이브러리입니다. Go, Java, C#, Python의 고정 참고 저장소 8개를 로컬 FTS5 데이터베이스에 색인합니다. assertion 규칙, 검토 원장, 읽기 전용 관찰 패널을 제공합니다.
docindex
johnxu22786/docindex
workspace 문서(MD/PDF/DOCX/TXT)의 로컬 의미 검색 인덱스입니다. FTS5 BM25와 로컬 임베딩 하이브리드 검색, 줄 번호가 포함된 인용, 증분 업데이트를 제공합니다.
dsh-plugin-recall
truelove-dreamer/dsh-plugin-recall
모델을 위한 세션 간 메모리: 과거 모든 세션을 전문 검색(ctx.sessionQuery를 통한 SQLite FTS5)하고 가장 잘 일치하는 발췌를 현재 컨텍스트로 가져옴
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-local-kb
hql6662/dsh-local-kb
Local full-disk knowledge base: indexes documents from C:/ and E:/ into a SQLite FTS5 trigram index over filename, body, and path, with a searchable DSH sidebar panel, no-keyword browse, usefulness/topic tags, and a token-efficient kb agent tool. Windows only; building the index needs a system Python 3 with PyMuPDF and python-docx (plus python-pptx and openpyxl for PPTX/XLSX), and no prebuilt index ships with the plugin.
dsh-session-coldstore
gnaneshkunal/dsh-session-coldstore
Tiered cold storage for DSH sessions: idle sessions move out of the live root into an on-disk cold tier instead of being deleted, an FTS5 index over that tier keeps them searchable, and a restore path moves a session back into the live root. Dry-run by default: nothing moves until you turn it off in Settings.
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-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-session-find
quecai-niu/dsh-session-find
Literal full-text search across every DSH session log (Chinese sentences work, where the built-in FTS5 tokenizer fails), as a right-sidebar panel that scrolls to the matching line, plus a session_find model tool.
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-memory
ascrm/dsh-memory
Local-first, file-backed memory plugin for DeepSeek Harness: Markdown memories, verified trust, per-turn recall, and optional SQLite FTS5.