Rag
haiku.rag is an MIT-licensed Python package for building local-first agentic retrieval-augmented generation systems. It supports document ingestion, embeddings, hybrid search, reranking, citations, and multimodal retrieval over user-owned documents without requiring a database server.
Overview
9 featuresRag is a RAG, search & retrieval project. It focuses on building a local document retrieval system with citations, hybrid search, and multimodal support without operating a database server. Rag is an open-source project aimed at developers building local RAG and agent applications. Rag is open source under the MIT license. Rag is available on the command line and API, and it can be self-hosted.
Gonzalo Gozalo builds and maintains Rag, and it first shipped in 2025. Development happens publicly on GitHub with 584 stars and 704 commits in the last 90 days. Key capabilities include document ingestion, hybrid search, and result reranking. It exposes integrations via an MCP server.
Summary written by a language model from the project’s public pages.
- Document ingestion
- Hybrid search
- Result reranking
- Citation support
- Multimodal retrieval
- Embeddings
- Agentic RAG
- Local-first operation
- MCP server
Built with & integrations
Trust & compliance
Indexing history
1What PulseGate has recorded for this listing
Frequently asked questions about Rag
- What is Rag?
- Rag focuses on building a local document retrieval system with citations, hybrid search, and multimodal support without operating a database server. It is catalogued under RAG, search & retrieval on PulseGate.
- Who should use Rag?
- Rag is an open-source project built for developers building local RAG and agent applications.
- Is Rag free?
- Yes — Rag is open source under the MIT license and free to use.
- What platforms does Rag run on?
- Rag runs on the command line and API. It can also be self-hosted.
- Is Rag still maintained?
- The GitHub repository shows 704 commits in the last 90 days.
- What projects are similar to Rag?
- Similar projects tracked by PulseGate include Rag, haiku.rag-slim, and CodeRAG.Raghaiku.rag-slimCodeRAG
- Who develops Rag?
- Rag is developed by Gonzalo Gozalo.
- When did Rag launch?
- Rag first shipped in 2025.
Similar projects
Closest matches by what these projects do