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.
About Muse Code on Product Hunt
“Meta’s terminal agent for long-horizon coding”
Muse Code launched on Product Hunt on August 6th, 2026 and earned 241 upvotes and 3 comments, placing #4 on the daily leaderboard. Introducing Muse Code, a terminal coding agent powered by Muse Spark 1.2, with persistent background agents, repository-scale execution, and built-in verification.
On the analytics side, Muse Code competes within Productivity, Developer Tools and Artificial Intelligence — topics that collectively have 1.7M followers on Product Hunt. The dashboard above tracks how Muse Code performed against the three products that launched closest to it on the same day.
Who hunted Muse Code?
Muse Code was hunted by Zac Zuo. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Zac Zuo
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.