A GitHub research preview plans each coding request as a multi-model workflow instead of a single model call.
Google's updated video model reads ten seconds of context, pins start and end frames, and renders drafts in…
AWS's new open-source benchmark runs agents against real resources in disposable cloud accounts.
LinkedIn's multi-agent review platform cross-checks suggestions across models and finds 63.9% get accepted.
Free Mode takes everyday tasks off the credit meter, powered by OpenAI's GPT-5.6 Luna, for subscription holders.
Slack Code turns project channels into shared workrooms where AI coding agents propose diffs and humans approve.
The AI code editor, now part of SpaceX, launched a rival repository platform that syncs with GitHub.
Warp Factories packages the agentic software factory into an off-the-shelf infrastructure layer for teams that cannot build their…
Developers report Claude Code returning empty thinking blocks while reasoning charges still apply.
The Chinese lab's open-source agent framework takes on Claude Code with an everything-is-a-plugin design.
Five major AI companies back a portable plugin format that packages agent skills and tools for any platform.
Meta's first coding agent pairs with the co-trained Muse Spark 1.2 model in a beta launch.