Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.

Run the latest LLMs and VLMs across GPU, NPU, and CPU with PC (Python/C++) & mobile (Android & iOS) support, running quickly with OpenAI gpt-oss, Granite4, Qwen3VL, Gemma 3n and more.

Local CLI Copilot, powered by Ollama. 💻🦙

CLI tool to produce MD context files from many sources, to help interact with LLMs (ChatGPT, Llama3, Claude, etc.).

V.I.S.O.R., my in-development AI-powered voice assistant with integrated memory!

Example of a Retrieval-Augmented Generation with Postgres, pgvector, ollama, Llama3 and Go.

Generate CLI commands for common tasks. Using Llama3.

AI-powered batch PDF renamer that works fully offline. Extracts text from each PDF, uses a local LLM to generate descriptive filenames, handles errors and invalid characters, and logs actions—no internet or external APIs required. Perfect for private, automated PDF organization.

api to chat with llama3 using groq

Go based client for Duckchat

Go client for groq.com

Yet another LLM Wrapper to use in CLI

Transforms all files in specified directory using a large language model like ChatGPT

Go-based command-line tool that uses AI to automatically generate meaningful commit messages for your Git repositories

Go implementation of Duckduckgo-chat api proxy to provide openai compatible API

Build multi-step AI workflows with schema-guided reasoning. Supports Ollama, LMStudio, OpenAI, OpenRouter, Gemini, and all latest models for structured generation, chaining, and data processing.

A Go based AI Agent REST API which generates multiple choice quiz questions with respect to the topic and difficulty given.

A PoC of RAG (Retrieval Augmented Generation) using pgvector with llama

Backend - Bedrock Trio: AWS, React & Go

A simple web-based chat application built with Go. This project serves static files and provides a basic chat interface using LLaMA3.