First release · macOS Apple Silicon
SophyAI picks, starts and publishes open-weight models on your Mac or on cloud GPUs rented by the hour.
The agents and editors you already use talk to an OpenAI endpoint that exists only on 127.0.0.1.
1 · Catalog
Each entry is model + inference engine + hardware, with measured hourly cost and speed. Choose by budget, VRAM or quality.
2 · Run
On your Mac with Ollama, ds4 Metal or Colibrì. When you need a large model, a GPU on Vast.ai starts, works and shuts down.
3 · Publish
One OpenAI endpoint on 127.0.0.1:8800/v1: several sessions and local models together, selected by ID (sophy/… or ollama/…). Cursor and OpenCode never see the provider.
4 · Agents
AI agents read the catalog, sessions and costs with read or manage scoped keys that expire.
1
On the portal, in a minute. The 14-day Pro trial starts right away, no card needed.
2
Max, Pro or Team, monthly or yearly. Payment goes through Stripe.
3
As soon as Stripe confirms, the app receives this month's signed license. No code to copy.
Native app (Tauri) for Mac. It holds the offline catalog, chat, the local gateway and model management. Windows and Linux come later.
A Docker service that keeps accounts, licenses, wallet and cloud sessions. The app connects with a personal key; the monthly license is signed and can be verified offline.
A private store of model weights, checked with SHA-256 against the originals. A wrong checksum and the model won't start.
Free, Max, Pro or Team: it sets how many hours a day you use the app. You pay us, monthly or yearly.
Pay as you go: a registered provider key (Vast.ai) and credit in your wallet. Every session shows its cost before it starts and stops when you stop it.
Model news · 2026-10-16
Aleph Alpha releases an open-weight MoE for German and English, with 3.46 billion active parameters. Here is the architecture and the minimum hardware, from one H200 to two H100s.
Model news · 2026-10-16
Meta's new open-weight MoE reads text, images, audio and video. We examine the architecture and the hardware it actually needs, from a 512 GB Mac to four Blackwell GPUs.
Model news · 2026-10-16
NVIDIA's new open model reads text, images and video with 12 billion active parameters. Here is the hardware it actually needs, from one H200 to an RTX PRO 6000.