플러그인

Insta360 GO 3S용 자동 일일 콘텐츠 파이프라인: 수족관 영상의 BLE/WiFi 원격 촬영, 무선 가져오기, 의사결정 로그가 있는 ffmpeg 품질 평가, 자동 편집(세그먼트 선택, TTS 내레이션, 음악, 자막), biliup을 통한 Bilibili 업로드(기본값은 드라이런).

DeepSeek Harness용 Kimi WebBridge 호스트 플러그인: 로컬 kimi-webbridge 데몬을 통해 사용자의 실제 브라우저를 구동하는 모델 도구(탐색, 스냅샷, 클릭, 입력, 평가, 스크린샷, 네트워크 검사, 탭 관리)를 제공합니다.

DeepSeek Harness용 로컬 시맨틱 코드 검색: 프래그먼트 수준 심볼 인식 인덱싱, 오프라인 어휘 임베딩 또는 OpenAI 호환 엔드포인트, RRF로 융합된 하이브리드 벡터 + BM25 검색 - 3개의 dsh 도구와 sema CLI를 제공합니다.

계보를 갖춘 결정·목표 메모리. 명시적 명령과 모델 도구가 결정을 결정론적으로 기록하고, 상태 카드가 compaction을 넘어 결정을 재고정합니다. BM25+jieba 검색을 갖춘 무손실 이벤트 스트림이 이를 뒷받침하며, 시나리오 수준의 충실도 회귀 스위트가 릴리스를 게이트합니다.

메인 대화 옆의 네이티브 나란히 채팅: 완전한 네이티브 UI를 갖춘 독립 아카이브 DSH 세션으로, 부모 컨텍스트 온디맨드 검색, 선택 인용, 유지 또는 삭제 수명 주기를 제공합니다.

가이드형 케이스 작성, 단언, 웹 비교 보고서, 복구 및 정책 게이트를 통해 재현 가능한 DSH 프로필 및 패치 실험을 실행합니다.

DeepSeek Harness를 위해 30가지 클래식 오픈소스 테마 팔레트(Catppuccin, Nord, Tokyo Night, Gruvbox, Solarized 등)를 공식 ThemeService 토큰에 매핑하고, 색상/폰트/모서리 반경을 실시간으로 조정하는 Style Settings 패널과 설정 팩 공유를 위한 JSON 내보내기/가져오기를 제공합니다.

개발 전에 로컬 코드와 GitHub/npm을 조사해 재사용 가능한 구현을 찾고, 재사용과 재작성의 차이를 평가하며, 아키텍처 결합도를 점검한다.

현재 세션에서 사용할 수 있는 스킬을 스캔하고 최근 대화와의 관련성에 따라 순위를 매깁니다.

DeepSeek Harness용 모델 네이티브 메타 에이전트 플러그인: 다섯 가지 에이전틱 워크플로 패턴(프롬프트 체이닝, 병렬 워커, 라우터, 슈퍼바이저, 평가 루프)으로부터 모델이 런타임에 작업별 워크플로를 합성하고 도구와 서브에이전트를 조율

md/txt/docx/pdf로부터 감사 가능한 KB 팩(SQLite FTS5)을 구축하며, 결정적 검색과 원문 읽기 지원

Prior-art search for an idea: three tools find similar open-source projects on GitHub, rank them by a score computed in code from a relevance judgement and the star count, then read the chosen repositories (README, dependency manifest, directory tree, key files) and report the class and function declarations found in each file header; files_read lists what was actually fetched.

All-in-one local memory: JSONL files per scope (session, project, global, or a custom name) with per-scope dedup, four model tools (memory_save, memory_search, memory_list, memory_forget), automatic recall injected into agent pre-step, and a settings panel. Retrieval combines lexical IDF with a local embedding backend, which the panel can install and manage itself.

Routes DSH web search through the current session's model and a self-hosted retrieval backend.

A Cyrene-themed agent for DSH, with a customizable look (palette, wallpaper, particle effects, background music, typing sound) and a code security scan. It carries a worldbook, long-term memory and a speech-style correction layer (every reader gets their own Cyrene), plus retrieval over the script to back up its answers.

Cross-compaction memory for a long session: on compaction it stores what is being dropped, and at question time it injects a few relevant passages (or nothing) so the model can recall what you decided before.

Memory-assembly team for DeepSeek Harness: every message triggers a five-step cognition loop (judge, retrieve, assemble, feedback, calibrate) carried by role-playing subagents (judge, retriever, archivist, advocate, editor, scribe), using BM25 retrieval, time-ordered material, and LLM assembly to build useful material packs injected into linghun. Works with dsh-linghun.

Turns a local Obsidian vault into a dedicated RAG chat panel: a sidebar page with the note browser, the retrieval-augmented chat and the cited source side by side, answering from fully local BM25 plus CJK-bigram retrieval over your notes and streaming through the DSH model channel, with clickable \[n] citations and mtime-based incremental indexing.

Read-only Skill inspector for DeepSeek Harness. It shows which Skills a conversation actually loaded — from observed loading evidence only — and which Skills the current environment can discover, and gives each Skill a detail page whose left column switches between the framework, the evidence, validation, evaluation, step evidence, run logic, the before/after of a modification when there is one, the definition facts and the raw SKILL.md. Declaration and run stay apart: the body is split into structure, declared workflow and progressive disclosure, the run logic is read from local receipts, and every declared step carries its own evidence — no observed evidence is reported as exactly that, not as executed or not executed, and the run's instruction hash sits beside the current definition as match, mismatch or unavailable. The evidence view gives each subject one of three states (declared, observed, unavailable), walks definition → load → use → outcome, names what each stage cannot reach, declines to attribute an outcome to the Skill, and can copy the snapshot out as byte-stable JSON. Validation checks the Agent Skills open standard and the platform profiles separately, each finding on a rule id and labelled standard compliance or platform compatibility. Evaluation keeps repeatable cases with the conditions each run was recorded under and the four stages of runtime evidence, comparing two runs of one case item by item without scoring them. The trigger boundary keeps should-trigger and should-not-trigger prompts, has you run them in a real new session, then records what was observed — whether a load record appeared and whether it was model-invoked or user-explicit; a typed /name is not a natural trigger, and an absent load record is reported as not observed, not as not triggered. The same projections are exposed to the agent as a read-only skill_review tool, which returns a structured review packet and says what it omitted when the packet will not fit whole. The inspector, the evidence chain and these reviews are computed on this machine from the definition and the session receipts; the Chinese reading version sends the body through the host's model when you ask for it, keeping code fences, paths and frontmatter verbatim and storing the result on this machine. A Skill can also be cloned into a local copy. It does not write back to the source Skill and does not run its scripts.

Reflect2Evolve memory plugin: layered L1/L2/L3 memory, reflection-weighted value backprop, cross-task policy induction, skill crystallization, and three-tier retrieval for OpenClaw, Hermes Agent, and DeepSeek Harness.

Windows system-drive (C:) cleanup for DSH: rule-based scan, five-tier safety grading, a staging area with a rollback ledger, UAC elevation, and migration to another drive — a model tool plus a Web GUI panel.

Language-pack framework that rewrites model replies: A is an independent LLM rewrite, B injects FTS5 terminology retrieval into that rewrite, C applies local dictionary and regex rules, and composite runs a pipeline such as B then A then C. Ships a GitHub pack marketplace, a ZIP installer with path, size and file-type checks, and a mandatory risk disclaimer gate.

Persistent project intelligence and memory plugin for DSH: architecture analysis, cross-session context, TODOs, and optional hybrid retrieval

Compares existing DSH sessions or runs controlled A/B trials between agent presets, showing aligned timelines, paired metric deltas, explicit success checks, and exportable reports.