Muse Code · CLI coding agents · crystl
models and pricing
Muse Code runs Meta’s Muse Spark model family, co-trained with the agent; other providers and local models are not supported. Subscriptions run from Everyday at $5/mo to Maximum at $200/mo, with usage multipliers at each tier, and pay-per-token billing through a Meta Model API key is also available.
what it’s good at
Muse Code fans large jobs out to persistent sub-agents in isolated git worktrees, and its headless mode suits scripts and CI pipelines. A TypeScript SDK and cross-session messaging support building on top of it, and it runs on macOS, Linux, and Windows.
Muse Code in crystl
Muse Code runs in a crystl shard with its own model selection and activity visibility, and a prompt can be handed to it at launch for one-shot worker runs. Crystl recognises the agent and tracks its activity, but the deeper surfaces are still unwired: its tool calls raise no approval cards, its sessions have no transcript crystl can read, and no resume command is documented for it.
A spawned Muse Code worker reports done when its process exits rather than on a turn-end hook.
The profile describes what crystl has tested; it never supplies a command, hook script, or launch setting. Those remain local to the Crystl installation.
Is Muse Code any good?
Votes from visitors who have used Muse Code, one per category per person. Community opinion, separate from the verified facts above.
as a daily driver
no votes yet
in large codebases
no votes yet
for CI and automation
no votes yet
value for money
no votes yet
crystl compatibility
How it runs in crystl
—Approval cards not verified
—Ask-user prompts not verified
—Transcript history not verified
—Session resume not verified
—Prompt injection not verified
✓Model selection supported
esc↑ ↓ navigate↵ openesc close