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 à double graphe de connaissances pour notes Markdown : graphes de prérequis + de similarité (parcours P/S-Agent), découpage par paragraphe, recherche hybride n-gramme/embedding et boucle explicite de retour de pondération — via 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.

Indexe les symboles de l'espace de travail avec Tree-sitter et fournit une recherche de code lexicale ou assistée par embeddings en option.