Helix AI Studio
One prompt → Claude, GPT, Gemini & Ollama work together
What it does
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.
Does the same job
all alternatives →
- IRI Remade the Fake Google Gemini Demo, Except Using GPT-4 and It's Real2023 · sagittarius.greg.technology · ▲434
- COCactus – Ollama for Smartphones2025 · github.com · ▲231
Hey HN, Henry and Roman here - we've been building a cross-platform framework for deploying LLMs, VLMs, Embedding Models and TTS models locally on smartphones. Ollama enables deploying LLMs models locally on laptops and edge severs, Cactus enables deploying on phones. Deploying directly on phones facilitates building AI apps and agents capable of phone use without breaking privacy, supports real-time inference with no latency, we have seen personalised RAG pipelines for users and more. Apple and Google actively went into local AI models recently with the launch of Apple Foundation Frameworks…
- MCMysti – Claude, Codex, and Gemini debate your code, then synthesizeDec 2025 · github.com · ▲216
Hey HN! I'm Baha, creator of Mysti. The problem: I pay for Claude Pro, ChatGPT Plus, and Gemini but only one could help at a time. On tricky architecture decisions, I wanted a second opinion. The solution: Mysti lets you pick any two AI agents (Claude Code, Codex, Gemini) to collaborate. They each analyze your request, debate approaches, then synthesize the best solution. Your prompt → Agent 1 analyzes → Agent 2 analyzes → Discussion → Synthesized solution Why this matters: each model has different training and blind spots. Two perspectives catch edge cases one would miss. It's like pair…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
