Plugins

Sistema de base de conocimientos estilo Cherry Studio para DeepSeek Harness (DSH): bases, documentos, fragmentación, embeddings (compatible con OpenAI / Ollama / local / reserva léxica), recuperación, herramientas orientadas a modelos y un panel de gestión en el navegador.

Integración de Feishu (Lark) para DeepSeek Harness: 25 herramientas para mensajes de chat e historial, documentos en la nube (incluidas páginas de base de conocimiento, gráficos e imágenes generados), registros de bitable, rangos de hojas de cálculo y permisos de Drive, usando tu propia app de Feishu empresarial de creación propia.

Gestor de base de conocimiento local para agentes DSH: importación multiformato, fragmentación con soporte CJK, búsqueda híbrida vectorial sqlite-vec + BM25 con rerank bge-reranker-base, instantáneas, exportación/importación kbpack y búsqueda entre KB — 22 herramientas de agente y un panel web.

Memoria local de tres capas para DeepSeek Harness: L1 memoria instantánea (MEMORY.md/USER.md) leída a demanda con las herramientas memory_* + L2 base de conocimiento buscable (hechos + SQLite FTS5, búsqueda en chino por tokenización de ventana deslizante) + L3 importación desde Hermes/Claude Code/Codex/WorkBuddy y desde documentos aprobados de Agent Hub (memory/global, memory/projects, decisiones aceptadas) con deduplicación por hash de contenido. La v0.2.0 eliminó toda inyección automática: la memoria entra en el contexto solo cuando el modelo llama a una de las 12 herramientas memory_*, y los datos permanecen en el disco local.

Espejo sin conexión de la documentación oficial de DeepSeek Harness como skill dsh: 168 páginas del sitio (EN/zh) más 52 documentos de referencia exclusivos del repositorio, con navegación por temas e índice de búsqueda de texto completo para desarrollo de plugins.

Knowledge base with a corrective acquisition loop for DeepSeek Harness: when the agent keeps hitting the same failure, a background worker fetches the web under a rate limit, distills the result into a staging area, and only a two-stage commit makes it recallable — pages without sources are refused.

Combines fault knowledge-base symptom-to-cause rules with similar past cases to rank candidate motor diagnoses with evidence terms and suggested extra tests.

Git-native, auditable long-term memory for AI agents

Brings the codebase knowledge-base capability of langchain-ai/openwiki into DSH — one-click generate/read/update of the repository Wiki, Grounded Claims (source-traced knowledge cards) and a project knowledge base built from uploaded local files, reusing the model DSH already has configured, with no second API key.

A living memory workbench for DeepSeek Harness: watch the Hindsight bank grow (7-day curve, recall heat, timeline) and manage knowledge pages and background tasks, with the local daemon auto-started by the plugin.

DSH plugin: auto-upload conversation progress to Tencent IMA (daily note + Work knowledge base), mirroring the local Claude Code ima-upload workflow

Trae tu historial existente de Claude / ChatGPT a DSH: importación instantánea sin tokens del memories.json dentro de una exportación de Claude, transcripciones locales de Claude Code sin necesidad de exportar y conversaciones destiladas mediante el modelo que ya tengas configurado en DSH. Cada memoria lleva evidencia literal verificada contra la fuente por código: una paráfrasis se descarta y se cuenta, y la evidencia hallada solo en turnos del asistente siempre se deriva a revisión en lugar de almacenarse.

Legal knowledge-base workbench: hybrid keyword/statistical/vector retrieval over local statute .doc/.docx corpora, faceted filtering, charge-name and civil-cause trees, a document editor, and four AI tools (citation check, contract review, AI analysis, AI drafting).

Code graph and knowledge base over an embedded FalkorDB: AST symbols, caller/callee tracing, refactor blast radius, affected-test discovery, clone detection, cross-language porting contracts and spec-to-code traceability.

loci second-brain sidebar tab: hybrid search, cited Q&A, day-grouped memory browsing and quick capture over a local loci knowledge base; proxies `loci serve-http` same-origin from dsh-better-sidebar, no core fork.

Create and configure Agent presets from a single settings section — persona prompt, a checked knowledge-base entry list injected into the system prompt, individual switches for four knowledge-base tools, per-Agent narrowing of MCP connections, and batch knowledge-base import.

On-demand memory for DeepSeek Harness: session logs are distilled into layered markdown (a summary, an index and per-topic files), and a mem_query tool returns only the matched entries rather than the whole index. Nothing is injected per turn, there are no dependencies, and every entry keeps a source pointer back to the conversation it came from.

几何论（共扼谱几何 CSG）知识库插件 for DeepSeek Harness：以 Markdown 文章为唯一真源，程序自动重建 BM25 索引、类型化主张依赖图与修复工作单并做一致性审计，附 869 条真理层与 SymPy 公式验证。开箱即用的离线知识库（31 个 geo_* 工具），零运行时依赖。Conjugate Spectral Geometry knowledge base plugin for DeepSeek Harness: offline BM25 retrieval, typed

Cross-session knowledge for DeepSeek Harness: ctx.knowledge service + knowledge_* tools, SQLite FTS5 trigram retrieval (CJK substring) with L1 query expansion. V1.11 contract (write/update/search/list/delete + budget + events + error codes).

Knowledge-base browser panel: tree browsing plus drag-to-cite (path-only or full content) into the composer.

Obsidian knowledge-base ingest workflow as a DeepSeek Harness plugin: a bundled skill provider + an obsidian_validate_vault model tool, all declarative and composable.

Offline BM25 knowledge base for the Conjugate Spectral Geometry (CSG) corpus: 208 articles / 3833 chunks / 871 verified truths, 5 geo_* tools (list / search / read / calc / truth) with LaTeX→Unicode rendering, truth→article citation chains and single-character query support, zero runtime deps, `dsh plugin add geometry-knowledge`.

RAGFlow knowledge-base retrieval plugin for the DeepSeek Harness.

The claude-obsidian-derived knowledge-suite skills (wiki, wiki-ingest, wiki-query, wiki-lint, save) as a DeepSeek Harness plugin, with attribution.