Open-source desktop app (MIT) that orchestrates Claude, GPT, Gemini and local Ollama in a 3-phase AI pipeline. Phase 1: Cloud AI plans the execution Phase 2: Local Ollama handles heavy processing (free!) Phase 3: Cloud AI synthesizes and quality-checks results ~60% of work runs locally at no API cost. Built with PyQt6 + FastAPI + React. Includes a Web UI accessible from phone/tablet on LAN, RAG document indexing, Discord notifications, and full Japanese/English i18n.

AppSignal — Real-time monitoring that helps you ship with confidence

Real-time monitoring that helps you ship with confidence

Hey Product Hunt! 👋 I'm the solo developer behind Helix AI Studio. I built this because I was frustrated switching between Claude, ChatGPT, and Gemini tabs all day. I wanted ONE app where all three work together automatically. The key insight: use each AI for what it's best at: • Claude/GPT → Planning & synthesis (high reasoning) • Local Ollama → Heavy repetitive processing (free, private) This reduces API costs by ~60% while getting better results than using any single model. It's MIT licensed, runs entirely on your machine, and includes a built-in Web UI so you can use it from your phone on the same network. Happy to answer any questions about the architecture or how the pipeline works! 🚀 GitHub: https://github.com/tsunamayo7/he...

AppSignal — Real-time monitoring that helps you ship with confidence

Real-time monitoring that helps you ship with confidence

Helix AI Studio

One prompt → Claude, GPT, Gemini & Ollama work together

One prompt → Claude, GPT, Gemini & Ollama work together