Meta Launches 'Muse Code' Terminal Agent with Replayable Runtime Architecture
JeremyCMorgan · x · 2026-08-14
Meta AI Research has released Muse Code (beta), a terminal coding agent powered by Muse Spark 1.2. It is designed to handle complex software engineering tasks across large repositories.
The major highlight is its runtime design:
- Event Log Mechanism: Uses an append-only local event log for every model call, tool run, approval, and edit.
- Crash Recovery: This single source of truth makes the runtime replay-exact and restart-safe. After a crash, the agent can resume precisely where it stopped, enabling it to handle long-running tasks.
- Persistent Background Agents: Features async background agents that remain active throughout the session, carrying out next steps to reduce latency and redundant information gathering.
It also ships with default skills like /plan, /grill, and /goal.
More from coding & agent
- Terminal Night 3 talk slides released, missing demo video to follow — 4310sy · 2026-10-16
- Agent developers are sitting on unused API credits that can exceed actual usage — EnvironmentalDay8864 · 2026-10-16
- Notion's bet on agents: abstract away deployment so users and agents just write code — simonguozirui · 2026-10-16
- Four Gemini 4 Argon agents beat Minecraft's Ender Dragon autonomously in 27 hours — Maxence Faldor · 2026-10-16
- Tencent's Terminal-RSI builds recursively self-improving terminal agents, hitting 19.84% on Terminal-Bench 4.0 — tencent · 2026-10-16
- Tsinghua's AutoSFT uses multi-agent collaboration to automate SFT data research — TsinghuaNLP · 2026-10-16