How Elyra's /rewind rolls back your conversation and your code together — atomically, with a safety net under the safety net.
A look at how Elyra prompts its models — and why less turns out to be more
Elyra v0.9.0 lets the coding agent save hard-won solutions as reusable skills — so the next session starts from what the last one figured out.
Two releases ago, we added Claude Opus 4.8. One release ago, we fixed how it thinks. Today, we let you control how hard it thinks — all the way up to a new setting called ultracode.
Anthropic published @anthropic-ai/sdk@0.100.0 to npm at 4:49 PM UTC today.
Most AI coding agents give you a config file and wish you luck. Elyra gives you a searchable settings menu you can open mid-conversation without losing your place.
No new features. No new tools. No new commands. Twenty fixes for the things that were quietly wrong under the surface — the three-second freeze, the silent failures, the slow leaks, and the crash that breaks your terminal.
Most of Elyra is natural language. But four single-character prefixes — !, !!, /, and @ — give you precise control over what the agent sees, what it doesn't, and how you steer the tool itself.
Two new commands. One lets you stop babysitting the agent. The other lets you stop leaving the agent to update it.
We spent the last few releases building extensions — LSP, SEO tools, workflow pipelines. Good features, all of them. But this release is different. Instead of adding new things, we made the tools you already use every minute of every session meaningfully better.