CouncilAI: local desktop app routing questions to 4 AI models
CouncilAI is a Windows desktop app that runs four local AI models and routes user questions to the appropriate model based on complexity. Simple questions use a fast lightweight model, while complex ones trigger deliberation where multiple models answer and the best response is selected. It operates fully offline on the user's hardware, requiring no accounts or cloud services.
Related
Open-source private desktop AI overlay with MCP support
Wisp is a desktop overlay that lets you invoke AI from any app via keyboard shortcuts, with context like text, screenshots, or active window. It supports voice queries, dictation, and pasting results directly, keeping data local and private.
Founder runs full multi-agent content pipeline offline on local laptop
A founder demonstrates a multi-agent pipeline for content research, drafting, and editing that runs entirely on a local laptop with no internet connection, using models stored on the hard drive. This showcases the growing capability of local AI to replace cloud-dependent workflows, eliminating API costs and data privacy concerns.
Conw.ai: lightweight self-learning AI with personality
Conw.ai is a 500M parameter AI model that runs locally on an iMac. It features self-learning capabilities and a distinct personality, aiming to provide a conversational AI that can adapt and engage users in a more natural way.
Luna OS: AI-powered desktop assistant for local use
Luna OS is an AI-powered desktop application that acts as a local assistant. It uses LLMs to provide useful assistance directly on the user's machine, aiming to be a practical alternative to cloud-based assistants. Built for a hackathon, it targets developers and users who want an AI assistant that runs locally.
Billy Bassistant AI Fish: AI assistant with local file knowledge and status LED
Billy Bassistant AI Fish is a voice-enabled AI assistant that can be fed custom PDF, Excel, or text files organized into topic-specific folders. It uses LLMs to process these local files and answer questions based on them, and optionally shows a status LED indicator. It solves the problem of having a physical AI assistant that can access and reason over personal documents.
