Replying to @helloshiva0801
We feel the same too!
And for models, you can identify which model suits your device spec in the app itself
We built the best experience for local AI on MacOS
Introducing Result for Mac
> Computer Use with local models
> One-click connection to private inference: DGX, Halo, etc
> Use open-weight cloud models
> Access models running on your Mac on your iPhone
result.dev/mac
Cloud VMs keep getting hacked, so we built the first on-device iPhone agent
Introducing Result
> Cards & passwords stay on-device
> Run openweight models on your compute or cloud
> Native Apple Pay & Passwords
> Works in the background even when locked
result.dev/ios
Sodium turns your source code into agent tools.
→ Finds routes, forms, and actions
→ Generates typed tools with safety rules
→ Signs and registers them through WebMCP
Your repository code never runs.
Most agent analytics platforms stop at crawlers, pageviews, and referrals.
Sodium measures what agents do after they arrive.
→ Tool called
→ Success or failure
→ Execution time
→ Top intent
Add one line of code.
→ Connect your repo
→ Review the tools
→ Install once
Sodium registers the approved tools through WebMCP.
Agents can call the actions already in your product.





