Meta Launches Muse Code: A Terminal Coding Agent with Async Multi-Agent Collaboration
ns123abc · x · 2026-08-06
Meta's Superintelligence Labs has officially released Muse Code (beta), a terminal coding agent powered by the newest model, Muse Spark 1.2. The tool is designed to handle complex software engineering tasks across large repositories, including planning changes, writing code, and validating results.
Key Highlights:
- Multi-Agent Collaboration: Features a main agent loop paired with async background agents. These persistent agents remain active throughout the session, proactively carrying out next steps and reducing redundant information gathering to lower latency.
- Fault-Tolerant Runtime: Utilizes a local event log for all operations, ensuring replay-exact recovery after crashes and enabling stable execution of long-running tasks.
- Bundled Skills: Ships with built-in commands like /plan (generates an approval-gated plan), /grill (stress-tests the plan), and /goal (executes toward a specific objective).
According to reports, the underlying model ranks #2 globally on the Terminal-Bench, outperforming strong competitors like GPT 5.6 Terra and Grok 4.5.
Related event: Meta Launches Terminal Coding Agent Muse Code(32 posts)→
More from coding & agent
- Stop Reviewing Your Agent's Plan: Best Practices for AI Workflows — msg · 2026-08-06
- Hermes Desktop Update: Agent Can Autonomously Control In-App Browser — Teknium · 2026-08-06
- Developer Questions the Point of Code Review Bots in the Age of AI Agents — mattrickard · 2026-08-06
- My Co-Founder Quit. So I Replaced Him with an API Key — LinusEkenstam · 2026-08-06
- AI Agents Reshape Drug Discovery: Experts Discuss Isomorphic's Prospects — xhluca · 2026-08-06
- PrintingPress: Automatically Turn Any API into an Agent-Native CLI — EXM7777 · 2026-08-06