EduSphere is an AI-powered academic assistant that turns raw transcripts into personalized insights, course paths, and scholarships — powered by local LLM inference. Built with a Golang Fiber backend and React (Vite) frontend, it integrates Generative AI reasoning, natural language interaction, and real-world data into a cohesive, production-grade.

Local LLM proxy, DevOps friendly

🚀 Enterprise-grade AI coding assistant with local AI processing, GitHub integration, and web scraping capabilities. Built with Go and powered by Ollama.

Local agentic CLI coding assistant

Kubernetes operator for GPU-accelerated LLM inference - air-gapped, edge-native, production-ready

Ultra-Concise Local LLM Library for Go

Local LLM debate arena — make two models battle any topic offline, third model judges. 100% local, no cloud.

AI-Native Autoscaler for Docker Compose — built with cagent + MCP + Model Runner.

Read PGS (Bluray) and VobSub (DVD) image subtitles and extract their text using external Vision Language Models.

RAGO (Retrieval-Augmented Generation Offline) is a fully local RAG system written in Go

A comprehensive Go client library for LM Studio, providing easy access to local language models for chat completions, embeddings, tool calling, and model management.

A high-performance task queue management system for Ollama models, built in Go.

Stop paying for AI APIs during development. LocalCloud runs everything locally - GPT-level models, databases, all free.

Terminal UI for locally hosted large language models

🤖 The free, Open Source alternative to OpenAI, Claude and others. Self-hosted and local-first. Drop-in replacement for OpenAI, running on consumer-grade hardware. No GPU required. Runs gguf, transformers, diffusers and many more models architectures. Features: Generate Text, Audio, Video, Images, Voice Cloning, Distributed, P2P inference

Nous: A privacy-focused personal knowledge assistant using local LLMs to securely interact with your documents and enhance information retrieval.

Ollama library wrapper