Posts tagged with #multi-agent
DEEP DIVE· 2 min read
Agent fan-out and git worktrees: parallel edits without collisions
Parallelism is easy to promise and hard to make safe. Muse Code’s answer is old, boring git technology used exactly right.
Read the post →DEEP DIVE· 3 min read
Why Muse Code keeps its agents alive all session
The quiet architectural decision behind Muse Code’s speed: background agents that persist for the whole session instead of being spawned per task and thrown away.
Read the post →