AI Decision System
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: experiment promotions, typed model answers and human-approved actions.
翻译准备中
Generic markdown collection MCP server with FTS5 + semantic search, frontmatter-aware indexing, and incremental reindexing
翻译准备中
取自仓库 README
正在加载完整 README。 以下为已保存的摘录。
Generic markdown vault MCP with hybrid search
• Hybrid search: SQLite FTS5 keyword search (BM25, porter stemming) and semantic search (FastEmbed, Ollama, OpenAI, or Voyage AI embeddings, plus any OpenAI-compatible endpoint via OPENAI_BASE_URL), fused with Reciprocal Rank Fusion; diversity-aware ranking returns sentence-scale snippets with full-section recovery via read(path, section=heading). See the Embeddings guide, including the recipe for OpenAI-compatible endpoints.查看完整 README ↗目前无法加载完整 README。请通过原文链接阅读。 以下为已保存的摘录。
Generic markdown vault MCP with hybrid search
• Hybrid search: SQLite FTS5 keyword search (BM25, porter stemming) and semantic search (FastEmbed, Ollama, OpenAI, or Voyage AI embeddings, plus any OpenAI-compatible endpoint via OPENAI_BASE_URL), fused with Reciprocal Rank Fusion; diversity-aware ranking returns sentence-scale snippets with full-section recovery via read(path, section=heading). See the Embeddings guide, including the recipe for OpenAI-compatible endpoints.查看完整 README ↗