Produchive: offline desktop activity monitor with local LLM analysis
Produchive is an open-source, offline desktop app for activity monitoring and productivity tracking. It stores all data locally in a JSON file and uses WebGPU to run open-source LLM models on-device for analysis, ensuring privacy. The app helps users who procrastinate on their PC to monitor their activity without their data being sold.
Entities
Related
Open-source desktop agent for local computer use, browser control, and file/code tasks
EverFern is an open-source (MIT) desktop agent that performs computer use, browser control, and file/code tasks entirely locally. It uses LangGraph for agent orchestration and supports local models via Ollama/LM Studio or cloud providers. Aimed at users who want to avoid subscription fees and keep data private.
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.
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.
Local AI health data analyst using Claude on Garmin SQLite warehouse
A local-first tool that lets users query their Garmin health data via Claude, running analysis on a local SQLite database. It helps users find correlations in their biometric data (e.g., resting heart rate, HRV, sleep) without sending data to the cloud.
Site blocker Chrome extension to reduce digital distractions
A Chrome extension that blocks distracting websites to help users stay focused. The extension was built by a developer who struggled with distractions during college, starting as a rough class project and later rebuilt from scratch. No LLM usage is mentioned.