haiku.rag vs RAG for your documents
haiku.rag is an open-source MCP server for knowledge and memory. RAG for your documents is an open-source MCP server for knowledge and memory.
- haiku.rag is best for ask questions of a folder of pdfs with sources.
- RAG for your documents is best for ask questions about a policy folder.
- What it is
- haiku.rag is an open-source MCP server for knowledge and memory.RAG for your documents is an open-source MCP server for knowledge and memory.
- Best for
- Ask questions of a folder of PDFs with sourcesAsk questions about a policy folder
- Kind
- MCP serverMCP server
- Pricing
- Open sourceOpen source
- Platforms
- CLI, self-hosted, Linux, macOS, WindowsCLI
- Runs
- LocallyLocally
- Open source
- Good for
- Ask questions of a folder of PDFs with sources; Give Claude Desktop a private document search; Check an answer by viewing the cited pageAsk questions about a policy folder; Verify that an assistant's answer is supported by your files; Prototype document search without cloud services
What haiku.rag does
Cited answers
Page numbers and section headings accompany answers.
Visual grounding
Highlights the cited chunk on the page image.
Hybrid retrieval
Vector and full-text search with optional reranking.
Sandboxed analysis
Runs Python across documents for computation.
Continuous ingestion
Filesystem, HTTP, S3 and WebDAV sources with a job queue.
What RAG for your documents does
Offline indexing
Indexes a folder at startup with no key, database or network.
Passage search
Returns ranked passages with source file and chunk id.
Answer checking
Tests an answer against retrieved or supplied sources.
Adjustable limits
topK and question size can be set by input or flag.
Stdio transport
The client starts the server directly.
haiku.rag vs RAG for your documents: questions
Is haiku.rag or RAG for your documents cheaper?
Both are open source. Compare current plans on each official site.
What is the difference between haiku.rag and RAG for your documents?
haiku.rag is an open-source MCP server for knowledge and memory. RAG for your documents is an open-source MCP server for knowledge and memory.