ChatGPT uses your Codex allowance. Claude runs through the official Claude Code app. Claude extra usage follows your own provider settings.
Connect once. Then just give it a task.
No files to download or unzip yourself. Run one setup command, then sign in with your provider.
- Open Terminal on your Mac.
- Copy this command, paste it into that window, and press Enter.
- Complete your provider’s sign-in. ACENET connects automatically.
Waiting for your computer to connect…
This private setup command expires in 10 minutes.
Setup installs the helper and any missing software automatically, then starts it when you sign in to your computer. Keep your computer awake while tasks run.
Use the downloadable helper instead
Unzip, open Start-ACENET, and enter this code:
Windows setup remains preview pending testing on a Windows device.
Your connected apps
ChatGPT tasks use apps exposed by Codex. Claude tasks use connectors exposed by Claude Code. Only apps exposed by the native provider are available. ChatGPT uses provider-approved reads; Claude enables supported Gmail, Calendar, Drive, Airtable, Fathom, Exa and Notion reads. Other tools may require permission and be unavailable in background tasks. Connector calls and permission failures appear in task activity. Sending messages and external changes are not supported.
Open-source models
Your subscription plans and reviews. Choose a hosted free model or one on your computer to do the work.
Free models · no model downloads
Connect OpenRouter to run the body remotely. Task content is sent to OpenRouter and its model provider. Your subscription helper is still needed for planning and review.
$0 model pricing only. Free availability and request limits vary. No paid fallback. Your OpenRouter key is encrypted in your private ACENET account and supplied to your paired helper only for active tasks.
Use a model on your computer instead
Install Ollama to get started ↗
Add a model
Downloads stay on your computer. Allow extra memory beyond the download size.
Qwen3 · 4BSmaller model · about 2.5 GB
Qwen3 · 8BLarger model · about 5.2 GB
First time using a local model?
- Install and open Ollama ↗ on the connected computer.
- Choose Download & use above. ACENET handles the model download and selection.
Already using LM Studio? Turn on its local server and load a chat model. ACENET will find it automatically.
If your helper is from an earlier version, reconnect using the latest download above. Hosted API providers and Ollama cloud models are excluded from this local picker.
Other subscriptions
Gemini and other providers are not connected in this release. A subscription is supported only when its provider permits an integration and a working native runner is available.
Claude preview requires a current, unmodified Claude Code installation. Provider terms. Native Claude sign-in and a response have been verified; the full workflow remains preview.