> [!NOTE] > This README was generated by [SKILL](https://github.com/agenvoy/skill-readme-generate), get the ZH version from [here](https://github.com/pardnchiu/KuraDB/blob/master/doc/README.zh.md). ***

DROP FILES IN, LET YOUR AGENT SEARCH THEM OUT

*** > A Go read-only file database with automatic Markdown conversion, English keyword indexing, and agent retrieval tools > [!WARNING] > **Redesign in progress**: Download a [release](https://github.com/pardnchiu/KuraDB/releases) build instead of compiling from source for now. See the [Roadmap](#roadmap) for progress. ## Table of Contents - [Positioning](#positioning) - [Roadmap](#roadmap) - [License](#license) - [Author](#author) ## Positioning > [!NOTE] > **Why no vector search** > - Every document has to be split into chunks and embedded, and semantic matching still falls short on precision. > - Vectors have to stay resident in memory, which does not scale in the long run. > - "Kura" (蔵) means storehouse; vector search belongs to [ToriiDB](https://toriidb.pardn.io). KuraDB returns to its name and focuses on storage and retrieval built for agents. > [!NOTE] > **Why no tokenizer** > - The language of incoming data is unknown in advance, and no tokenizer segments every language well, so gse tokenization has been removed. > - An LLM generates English keywords for each section while the original text stays intact; queries then use English keywords, so data in any language is found the same way. - **Drop-In Conversion** — Files dropped into `~/Kura_{name}` are converted to Markdown and stored in SQLite with their original-language content intact. - **Cross-Language English Keywords** — An LLM generates English keywords for each section, indexed by SQLite FTS5, so retrieval depends on neither per-language tokenization nor vectors. - **Agent Retrieval Tools** — `list`, `search`, and `read` let an agent browse the data, locate sections by keyword, and expand context by line range. - **One-Way Read-Only Boundary** — The API serves queries only; the sole write path is watcher → conversion → SQLite. ## Roadmap | Phase | Scope | Status | |---|---|---| | Phase 1: Remove vector dependencies | Remove OpenAI embedding, the vector cache, semantic search, and the query cache; remove gse tokenization and match queries split on whitespace against the original text for now | Done | | Phase 2: New storage | Store each file as one Markdown document, split it into sections by heading, page, slide, or table rows with line numbers, attach English keywords, index them in FTS5, and add HTML conversion | Planned | | Phase 3: Retrieval tools | Replace the MCP and HTTP interfaces with `list`, `search`, and `read`, rank search with bm25 and return line ranges | Planned | Supported formats: plain text, Markdown, PDF, DOCX, PPTX, CSV/TSV, XLSX, and HTML (added in Phase 2). ## License This project is licensed under the [MIT LICENSE](https://github.com/pardnchiu/KuraDB/blob/master/LICENSE). ## Author Just [open an issue](https://github.com/pardnchiu/KuraDB/issues/new) to share an idea.