Google releases AX, an open-source Kubernetes-style orchestrator that runs autonomous AI agents in sandboxes across clusters using Task, Workspace, Gateway and Model primitives, while warning that its still-evolving protocols may undergo major breaking changes before a stable release.
Meta launches the SAM 3.1 API, letting developers use text prompts to detect, segment and track objects across video while preserving identity, with no model hosting or fine-tuning required and pricing starting at $2.50 per 1,000 images.
Vercel Labs releases json-render v0.21.0, adding experimental composition APIs and a playground model option while constraining AI-generated interfaces to developer-defined component catalogs, schemas, and actions.
mizorewww launches Laya-MLX, a native Apple Silicon runtime for Convai Innovations’ typed decision models that runs without text generation, PyTorch, or cloud APIs, reporting 7.39 ms median latency for its 322M multilingual model on an M3 Max.
Anthropic adds AGENTS.md support in Claude Code 2.1.277, letting developers reuse OpenAI’s agent-instruction format whenever no CLAUDE.md file is present and toggle the behavior through /config.
Typesafe AI emerges from stealth with Jev, a software-to-software model it says delivers frontier-level intelligence for just over 4 cents per million input tokens, backed by $40 million and developed by former OpenAI researcher Diogo Almeida.
Cloudflare open-sources a security-audit skill that guides coding agents through six audit phases and emits independently verified, machine-readable vulnerability findings, requiring confirmed bugs to include a complete source trace and bounded observed result while sandboxing target code with networking disabled.
Cua launches an open-source computer-use platform that lets AI agents operate native desktop apps and browsers across macOS, Windows and Linux through its Cua Driver CLI, MCP and typed SDKs.
Notion launches its Skills API, letting teams turn Notion pages into AI-agent skills that sync to GitHub and can be installed through Vercel’s Skills CLI with commands such as `npx skills add <notion url>`.
Tamara Tran launches fast-jev-compaction for Claude Code, using Jev-scored decisions to preserve user and assistant text verbatim while pruning obsolete tool calls and truncating unneeded results to a default 300-character head.