Muse Wonder
5.0 out of 5 stars
(1 Rating)
Muse Wonder is a frontier artificial intelligence model developed by Meta for personal assistance, professional workflows, software development, and autonomous agent tasks. The model combines Active Memory, which retrieves relevant information from previous conversations, with Active Focus, which supports sustained execution of complex, multistep assignments. Muse Wonder can assist with research, document analysis, financial and legal information, software engineering, and business process automation. Its agentic capabilities enable it to work across applications, use contextual information, adapt to obstacles, and request clarification or approval when necessary. The model supports coding activities ranging from small application development to complex software projects involving repeated testing and revision. Muse Wonder is available through the Meta Model API and Muse Code, with additional integration into Meta's Muse assistant planned for future releases.
Learn more about Muse Wonder
Muse Ember
Muse Ember is an efficient multimodal AI model developed by Meta for autonomous agents, software engineering, complex reasoning, and high-volume task automation. The model specializes in repetitive agentic operations such as tool calling, code analysis, information extraction, workflow routing, and document processing. It supports text, images, audio, video, and PDF inputs with a one-million-token context window and a maximum output length of 512,000 tokens. Muse Ember can execute multistep business workflows, analyze large software repositories, perform coding tasks, and interpret visual information from documents and screenshots. Its cost-efficient architecture makes it suitable for multi-agent systems in which larger models handle planning while Muse Ember executes frequent subtasks. The model is available through Meta Model API and Muse Code, with API pricing starting at $0.10 per million input tokens and $0.50 per million output tokens.
Learn more about Muse Ember
Muse Spark 1.2
5.0 out of 5 stars
(1 Rating)
Muse Spark 1.2 is Meta’s coding-focused model update designed to power Muse Code and improve software engineering workflows. The model is built for code generation, complex debugging, codebase understanding, long-horizon development tasks, and end-to-end developer workflows. Muse Spark 1.2 was co-trained with Muse Code to improve performance inside the terminal coding agent environment. It supports planning, goal conditioning, context compaction, subagent coordination, and iterative coding workflows across large repositories. The model was trained with expanded coding compute, diverse development environments, self-improvement loops, and long-running engineering tasks. Built for AI developers and software teams, Muse Spark 1.2 helps agents plan, write, validate, debug, and optimize code with greater autonomy.
Learn more about Muse Spark 1.2
Muse Code
5.0 out of 5 stars
(1 Rating)
Muse Code is Meta’s terminal coding agent, powered by Muse Spark 1.2, for handling complex software engineering tasks across large repositories. The agent can plan changes, write code, validate results, and coordinate multiple persistent subagents during development sessions. Muse Code uses async background agents that stay active throughout a session to reduce repeated information gathering and help complete multi-step tasks with less steering. Its runtime uses a local event log that records model calls, tool runs, approvals, and edits so sessions can be replayed and resumed after failures. Muse Code includes bundled skills such as /plan for approval-gated planning, /grill for stress-testing plans, and /goal for working toward completion. Built for AI developers and software teams, Muse Code helps automate coding workflows, long-running engineering tasks, debugging, and repository-level development.
Learn more about Muse Code