skaldlabs/skald
Self-hosted RAG (Retrieval-Augmented Generation) platform that handles document ingestion, embedding generation, and retrieval with multi-language SDKs and MCP integration.

Skald provides a production-ready RAG system that can be deployed in your own infrastructure. It manages the complete ingestion pipeline including document parsing, intelligent chunking, summarization, tagging, embedding generation, and vector storage. The retrieval layer handles query rewriting and vector search to return contextually relevant results. The platform offers SDKs for Python, TypeScript, Go, Ruby, PHP, and C#, along with a Model Context Protocol (MCP) server for agent integration.
Frequently asked
- What is skaldlabs/skald?
- Self-hosted RAG (Retrieval-Augmented Generation) platform that handles document ingestion, embedding generation, and retrieval with multi-language SDKs and MCP integration.
- Is skald open source?
- Yes — skaldlabs/skald is an open-source project tracked on heatdrop.
- What language is skald written in?
- skaldlabs/skald is primarily written in TypeScript.
- How popular is skald?
- skaldlabs/skald has 563 stars on GitHub.
- Where can I find skald?
- skaldlabs/skald is on GitHub at https://github.com/skaldlabs/skald.