WebKit's Safari MCP server is available in stable Safari 27.0 as well as Technology Preview. It runs locally, but captured page data passes to the connected agent; remote automation must be enabled explicitly.
The self-hosted deployment platform's November 2 release changes how teams delegate infrastructure control. Existing integrations using write-only tokens for deletions may fail until explicitly reauthorised.
New RevenueCat growth tools bring web funnels, AI paywalls and early payouts into one subscription platform, with important eligibility and fee caveats.
Google is changing the default for Performance Max image extraction on December 4, 2026. Existing campaigns keep their settings, but new campaigns will opt in regardless of an account-level opt-out; agencies and SaaS ad tools need a campaign-level override and careful handling of repeated asset settings.
Grafana Pages goes beyond dashboard panels: prompt-built interactive pages can use connected telemetry and invoke external tools via MCP. It is a public Grafana Cloud preview, not a self-managed release.
A new public MCP endpoint lets agents search without an API key and complete shopper-authorised purchases. It is separate from the Global Catalog REST API retirement and earlier browser-only WebMCP checkout; webhooks are not available at launch.
The funding headline is less interesting than the workload signal: Supabase says agents now create most new databases on its platform, and it is buying Turso to handle higher-volume database creation for those workloads.
GitHub-hosted Actions jobs that use `ubuntu-latest` are about to change operating-system generation without a YAML edit; teams can test on `ubuntu-26.04` now or pin 24.04 while they migrate.
The important change is at the gateway boundary, not just inference placement. OpenRouter says prompts can now stay in-region from decryption through provider execution and supported server tools, while teams can enforce the rule per workspace, team or API key.
New paid Gemini API projects now default to store=true on generateContent, streaming and batch calls; older projects retain their settings. Developers can opt out per request or project.
Developers can now train and evaluate adapters through custom code while Together runs the GPU-heavy operations. The flexibility comes with B200-only support, a $100 credit threshold and ongoing charges for idle ready resources.
Google's distributed SQL database can now run in production beyond Google Cloud, but 'deploy anywhere' doesn't mean free or fully managed. Spanner Omni GA brings security, backup and paid commercial licensing, with important limits on its developer edition.
Meta has made the privacy-versus-price trade explicit in its Model API: developers can choose standard pricing or a contributor model ID with steeply discounted inference in exchange for training-data permission. The choice matters for proprietary code, customer data and AI SaaS workloads.
WordPress 7.2 will not ship wp_set_secret()/wp_get_secret(): a 17 November core revert removed the beta feature after permission and provider-design objections.
Codex 0.149.0 includes the async-message tool, delivery metadata and removal of the client-side feature gate that BTN previously tracked only on main. Parallel human-agent work is now in a stable client, but late replies can still race with decisions and model capability metadata remains the final exposure gate.
The November 16 Search Analytics API update unlocks brand and multimodal reporting for developers, with eligibility, historical coverage and client-library caveats.
Jev, CLM and GLiNER2.5-Decide made bounded software decisions look like a distinct model category. OpenAI is now validating the same architectural split with a Luna-powered API designed to answer finite questions rather than generate open-ended prose.
HIPAA support moves Laravel Cloud into a class of regulated workloads that shared application hosting could not safely claim. Private Cloud supplies dedicated tenancy, encryption, SSO/SAML, backups and a BAA path, while application-level access control, audit logging and PHI handling remain the developer’s responsibility.
Jev’s launch claims were interesting; Vercel’s usage data is more useful. Nearly 13% of paid AI Gateway teams tried the typed decision model in its first day, while Jev also rose to a material share of gateway requests. That does not establish retention or production success, but it is unusually fast developer uptake for a model designed to make bounded software decisions rather than generate prose.
Wiz's rolling AI-platform security tracker has new vendor-confirmed incidents and a second Fireworks intrusion; NEAR's SGLang exploitation shows why confidential enclaves do not secure vulnerable inference software.