quillrag runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 27 Aug 2026.
Single-binary local RAG MCP server in Rust. MiniLM compiled in, hybrid search, zero deps.
Nothing serious here today
Today is the operative word: we check quillrag every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Alternatives to quillrag
same job, measured the same wayLocal RAG MCP server with hybrid search, PDF/DOCX support, and zero-config setup
Local-first RAG MCP server: hybrid search over a folder of your own documents
Local, privacy-focused RAG service for code search via MCP. https://linggen.dev
AI-native runtime with built-in MCP server. 232 builtins, AI pipelines, RAG, single ~8 MB binary.
Build searchable AI research knowledge bases with hybrid vector search directly in Claude Desktop.
Minimal RAG-over-a-corpus MCP retrieval: search_knowledge returns cited chunks. Local embeddings.
MCP RAG server with hybrid search, multi-KB support, and AI-powered chunk contextualization.
Local FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.
quillrag — questions
Answers built from our own checks of this server.