DocuQuery: A private, local-first AI assistant that lets you upload documents and ask natural-language questions over them using Retrieval-Augmented Generation (RAG).

A modular Rust library for Retrieval-Augmented Generation (RAG) with Ollama integration.

Text-to-Vector embedding service (Rust, Tonic) (Q2:2025)

🎨 Visualize audio in your terminal with Chroma, a Rust-based ASCII art shader that offers GPU-accelerated effects and real-time configuration adjustments.

A RAG system managing personal knowledge. Powered by LLM. Written in Rust. Run locally.

Knowledge graph agent for personal knowledge management

it's not a hammer, chisel, or scalpel. but it's good enough for government work

Rust API client library for Trieve

An intelligent reading platform that combines fast chapter delivery with AI-powered contextual understanding

LLM documents spliting with AI agent that wrap chunks within document's context and store into a vector DB with simple chat

A simple vector database in rust

A RAG (Retrieval-Augmented Generation) example project

A state-of-the-art AI prompt compiler

Korvus is a search SDK that unifies the entire RAG pipeline in a single database query. Built on top of Postgres with bindings for Python, JavaScript, Rust and C.

your personal privacy focused ollama integrated CLI RAG

Blizz: a nomadic AI development toolshed

🐙 Meta-AI Orchestrator unifies multiple LLMs with dynamic routing, RAG search, and DAG pipelines for enterprise AI workloads across providers, with observability and QA.

CLI for automatic generation of embeddings

Retrieval-Augmented Generation Bot

A library to gather structured statistics on the source code files in a software repository, generate embeddings and store in a vector database.