High-performance lightweight proxy and load balancer for LLM infrastructure. Intelligent routing, automatic failover and unified model discovery across local and remote inference backends.

Use pre-trained, task-specific Small Language Models and fine-tune them without training data

Run IBM Granite 4.0 locally on Raspberry Pi 5 with Ollama.This is a privacy-first AI. Your data never leaves your device because it runs 100% locally. There are no cloud uploads and no third-party tracking.

A private, local RAG (Retrieval-Augmented Generation) system using Flowise, Ollama, and open-source LLMs to chat with your documents securely and offline.

Recallium is a local, self-hosted universal AI memory system providing a persistent knowledge layer for developer tools (Copilot, Cursor, Claude Desktop). It eliminates "AI amnesia" by automatically capturing, clustering, and surfacing decisions and patterns across all projects. It uses the MCP for universal compatibility and ensures privacy

LocalPrompt is an AI-powered tool designed to refine and optimize AI prompts, helping users run locally hosted AI models like Mistral-7B for privacy and efficiency. Ideal for developers seeking to run LLMs locally without external APIs.

Powers the local RAG pipeline in the BrainDrive Chat w/ Docs plugin.

Web-Based Q&A Tool enables users to extract and query website content using FastAPI, FAISS, and a local TinyLlama-1.1B model—without external APIs. Built with React, it offers a minimal UI for seamless AI-driven search

The high-performance brain for Turbo Cloud Gallery. Features Smart RAM caching, aggressive WebP compression, AI-powered memories (Ollama), and direct Telegram file smuggling. Optimized to run fast on low-end hardware.