Vibe Coding DiscoverLocal AI-powered document search and editing with first-in-class hybrid retrieval, LLM answers, WebUI, REST API and MCP support for AI clients.
Local-first knowledge engine that indexes Markdown, PDF, Office files and code with hybrid BM25 + vector retrieval, cited LLM answers, and MCP/REST/CLI/SDK surfaces. Ships a Web UI, daemon, and one-command MCP install for ten AI clients; no GPU or cloud required.
Use Cases
Search notes, PDFs, Office docs and source code in one local indexGive coding agents persistent local memory over docs via MCPAsk natural-language questions and get cited answers from your own filesHybrid BM25 + vector retrieval with explainable score tracesCompile bounded evidence Capsules for agent contextExpose retrieval through CLI, Web UI, REST API and TypeScript SDKQuick capture of provenance-rich notes into a knowledge baseOffline semantic search with no account or telemetry
Built With
- Language
- TypeScript
- Frameworks
- Bun · TypeScript · Model Context Protocol · REST · MCP SDK
Tags
local-first · rag · hybrid-search · bm25 · vector-search · semantic-search · embeddings · mcp · llm · knowledge-base · second-brain · cli · rest-api · offline · typescript · document-search