sqlite-vec is an extremely small, 'fast enough' vector search SQLite extension designed to run anywhere. It allows storing and querying of float, int8, and binary vectors using virtual tables, written in pure C with no dependencies. It supports storing non-vector data in metadata, auxiliary, or partition key columns. It is a Mozilla Builders project with additional sponsorship from companies like Fly.io, Turso, SQLite Cloud, and Shinkai.
BunkerM: All-in-one Mosquitto MQTT broker with Web UI for easy management, featuring dynamic security, role-based access control, monitoring, API and cloud integrations
A proof concept for an AI-powered hedge fund that explores the use of AI to make trading decisions for educational purposes.
Docling is a tool that parses documents and exports them to desired formats like Markdown and JSON. It supports various document formats and provides advanced PDF understanding, metadata extraction, and integration with LlamaIndex and LangChain for RAG / QA applications.
PocketPal AI is an application that brings language models directly to your phone, offering offline AI assistance and model flexibility for both iOS and Android devices.
An extension that automatically unloads and reloads your model, freeing up VRAM for other programs.
An open-source web browser project developed using web standards. It's in a pre-alpha stage, suitable for developers. The browser aims to be robust and secure with a multi-process architecture. It uses libraries like LibWeb, LibJS, and LibWasm for rendering, JavaScript, and WebAssembly, respectively.
The llmsherpa project provides APIs to accelerate Large Language Model (LLM) projects. It includes features like LayoutPDFReader for PDF text parsing, smart chunking for vector search and Retrieval Augmented Generation, and table analysis. It is open-sourced under Apache 2.0 license.
Mesop is a Python-based UI framework that allows you to rapidly build web apps like demos and internal apps. Easy to get started, fast iteration, and flexible & composable.
Open-source project showcasing a speech-to-text application on a low-cost CH32V003 microcontroller. The application reads audio from an analog microphone, identifies spoken digits 'zero' to 'nine', and logs the results over a serial link.
