Plugins

Cherry Studio-style knowledge base system for DeepSeek Harness (DSH): bases, documents, chunking, embeddings (OpenAI-compatible / Ollama / local / lexical fallback), retrieval, model-facing tools, and a browser management panel

RAG de doble grafo de conocimiento para notas Markdown: grafos de prerrequisitos y de similitud (recorrido P/S-Agent), fragmentación por párrafos, búsqueda híbrida n-gram/embeddings y un bucle explícito de retroalimentación de pesos, todo vía MCP.

Turns local markdown and text documents into a queryable knowledge base with hybrid semantic and keyword search, citation verification, and source injection.

Cross-session plaintext memory: deterministic BM25 keyword recall (no embeddings), memory_save/list/search/confirm/forget tools behind a human-confirm gate, and global + project-scoped JSON stores that follow your git repo.

Layered memory pipeline for DSH: auto-distills conversations into atomic facts, scene summaries and a persona profile (L0–L3), with hybrid BM25 + vector retrieval, chat/work family separation, and context injection before each model step.

Indexa los símbolos del espacio de trabajo con Tree-sitter y ofrece búsqueda de código léxica o, opcionalmente, asistida por embeddings.