people will compare the model. the more useful part might be how it runs
Summary
Meta released Muse Code beta with Muse Spark 1.2, positioning it as a third coding-agent option next to Claude Code and Codex. Its key differentiators are parallel sub-agents in isolated worktrees, persistent background agents, and local event logging for crash recovery, making it suited for long-running tasks on large repos.
Similar Articles
@cline: Muse Spark 1.1 just launched and it's their most capable coding agent model yet. On Terminal-Bench 2.1 it scores 80.0%,…
Meta launches Muse Spark 1.1, an upgraded coding agent model scoring 80.0% on Terminal-Bench 2.1, alongside a public preview of the Meta Model API.
Muse Code and Muse Spark 1.2
Meta releases Muse Code, a terminal coding agent, and Muse Spark 1.2, an upgraded coding-focused model with improved code generation, debugging, and long-horizon task handling.
Meta launches Muse Code, an AI agent for large code bases
Meta launched Muse Code, a terminal-based AI coding agent in beta that handles complex software engineering tasks across large codebases, competing with OpenAI's Codex and Anthropic's Claude Code.
Meta says its new AI model is ready to compete on coding
Meta releases Muse Spark 1.1, a new AI model for advanced coding tasks including bug detection and agentic workflows, available via the Meta Model API.
Meta releases Muse Code in beta
Meta has launched Muse Code, a beta coding tool aimed at assisting developers.