The runtime design is probably the most interesting part. A main agent loop works alongside persistent async background agents that stay active throughout the session, gathering context and handling supporting work without being recreated for every step.
Muse Code also keeps a local event log of every model call, tool run, approval, and edit. If a long task crashes, it can resume from the exact point where it stopped.
The multimodal demo is fun too. You can pass an .mp4 fly-through of a house into the terminal, and Muse Code can interpret the video and build a vacation home marketing and booking website.
The Contributor API pricing is unusually low if you’re comfortable with your content being used for product improvement.
Replies
Flowtica Scribe
Hi everyone!
@Meta is entering the terminal agent space with Muse Code, powered by the new Muse Spark 1.2 model.
The runtime design is probably the most interesting part. A main agent loop works alongside persistent async background agents that stay active throughout the session, gathering context and handling supporting work without being recreated for every step.
Muse Code also keeps a local event log of every model call, tool run, approval, and edit. If a long task crashes, it can resume from the exact point where it stopped.
The multimodal demo is fun too. You can pass an .mp4 fly-through of a house into the terminal, and Muse Code can interpret the video and build a vacation home marketing and booking website.
The Contributor API pricing is unusually low if you’re comfortable with your content being used for product improvement.
WebBrain
does it work in the us only? and how much?