News & deep dives.
Announcements, research notes, and practical guides on Muse Code, Muse Spark, and the Meta Model API.
The event log: replay-exact, restart-safe
Agents that work for hours need a memory that survives anything. Muse Code’s runtime is built around a single append-only log — and almost every trust property of the product falls out of it.
Read the post →Getting started with Muse Code: from install to first merge
Meta’s terminal coding agent is deliberately minimal to set up: one command, one browser sign-in, and you’re driving a multi-agent session inside your own repository. Here’s the whole path, including the parts worth slowing down for.
Read the post →An autonomous GitHub bot that knows when not to act
The cookbook’s GitHub agent recipe wires triage, PR review, and bug-fix automation into GitHub Actions on OpenCode and Muse Spark. Its most transferable lessons are the guardrails.
Read the post →One API, every harness: the Model API ecosystem play
Meta shipped its coding model everywhere developers already are — the OpenAI SDK, the Anthropic SDK, rival agent CLIs, even OpenRouter. Compatibility-first is the distribution strategy.
Read the post →Drop an mp4 in the terminal: multimodal coding, demonstrated
The most quietly radical launch demo wasn’t about speed or parallelism. It was a video file becoming a website.
Read the post →24 hours, 1,000 tool calls: what the kernel case study proves
Benchmarks measure an agent’s sprint. Meta’s kernel-optimization study measures its marathon — and it’s the more interesting number.
Read the post →How Muse Spark 1.2 was trained: co-training, long-horizon work, and a self-improvement loop
“Built for Muse Spark” isn’t marketing shorthand — it describes a training strategy. Three techniques from Meta’s release notes explain why the model and the agent perform better together than either would with a stranger.
Read the post →