What embedding options does Goldie support?

Goldie offers flexible embedding backends. You can choose between its built-in MiniLM model (processed locally via ONNX Runtime for offline use) or integrate with an Ollama instance, supporting a wide range of Ollama-compatible embedding models like nomic-embed-text.

How does Goldie manage document storage and retrieval?

Goldie uses SQLite with the `sqlite-vec` extension for persistent vector storage. It automatically chunks large documents with overlap to optimize retrieval, allowing for efficient semantic search and intelligent knowledge recall.

Can Goldie integrate with popular AI development tools?

Yes, Goldie is designed for seamless integration with AI agents and tools. It provides configurations and examples for connecting with Claude Code, Claude Desktop, and OpenAI Codex, enabling these platforms to leverage Goldie's local RAG capabilities.

What types of content can I index with Goldie?

Goldie can index various types of content, including raw text, individual local files, and entire directories. It supports glob patterns for directory indexing, recursive searches, and custom skip patterns (via `.goldieskip` files) to manage what gets indexed efficiently.

Goldie

Name: Goldie
Author: srfrog

bysrfrog

•

データサイエンスとML

開発者ツール

学習とドキュメンテーション

Provides a local Retrieval-Augmented Generation (RAG) server written in Go for semantic search and knowledge recall.

Goldie

bysrfrog

•

データサイエンスとML

開発者ツール

学習とドキュメンテーション

Provides a local Retrieval-Augmented Generation (RAG) server written in Go for semantic search and knowledge recall.

Goldie is a powerful, locally-run RAG server built in Go, designed to augment your AI interactions by providing context from your personal knowledge base. It allows you to index various forms of content, including local files, directories, and even past AI conversations, using either local MiniLM embeddings or Ollama models. By storing embeddings in a SQLite database, Goldie enables semantic search and intelligent knowledge recall, making your local data seamlessly accessible to tools like Claude Code, Claude Desktop, and OpenAI Codex for richer, context-aware responses.

主な機能

010 GitHub stars

02Multiple embedding backends: MiniLM (local via ONNX Runtime) or Ollama (supports various models)

03Local embeddings using all-MiniLM-L6-v2 model (384 dimensions)

04Persistent SQLite vector storage with sqlite-vec extension

05Automatic document chunking with overlap for optimal retrieval

06Semantic search, directory indexing, and intelligent knowledge recall

ユースケース

01Augmenting AI assistants (Claude Code, Claude Desktop, OpenAI Codex) with local, context-specific knowledge.

02Creating a searchable personal knowledge base from local documents, notes, and web content.

03Indexing and searching past AI conversation histories to find solutions, code snippets, and track project history.

Goldie

Snowflake Integration

Tinybird

Axiom

Diagram Maker & Visualizer

GH Issues Auto-Fixer

Discord Integration

Goldie

主な機能

ユースケース

Snowflake Integration

Tinybird

Axiom

Diagram Maker & Visualizer

GH Issues Auto-Fixer

Discord Integration

主な機能

ユースケース