Meta AI Releases Muse Code (Beta): A Terminal Coding Agent Powered by the New Muse Spark 1.2 Model
Meta
Anthropic
OpenAI
Google/DeepMind
Moonshot AI
xAI
Meta AI has released Muse Code, a terminal coding agent in beta, powered by its new Muse Spark 1.2 model. It targets complex software engineering across large repositories with persistent async background agents and a replay-exact, restart-safe local event log. The model is also available via the Meta Model API with expanded global access.
Meta AI has released Muse Code, a terminal coding agent in beta, powered by its new Muse Spark 1.2 model. The agent targets complex software engineering across large repositories: it plans changes, writes code, and validates results. A set of async background agents stays alive for the whole session instead of spawning per task. A local append-only event log records every model call, tool run, approval, and edit, which Meta calls replay-exact and restart-safe. Muse Spark 1.2 was co-trained with the harness itself. Meta also published a kernel-optimization case study running 1,000+ tool calls over as long as 24 hours. Muse Code ships in beta for macOS and Linux via curl -fsSL https://dev.meta.ai/install.sh | bash. The launch post does not mention downloadable weights, so treat this as a hosted dependency.
- Abbreviations
- API = Application Programming Interface — программный интерфейс приложения
- GPU = Graphics Processing Unit — графический процессор
- SaaS = Software as a Service — программное обеспечение как услуга
- KDA = Kernel Data Architecture (likely specific kernel type, not expanded)
- MLA = Multi-head Latent Attention (inferred, not in text)
Source: MarkTechPost —
original