Releasesby GlyphAsk mode for Agent Runners
Netlify Agent Runners now have a mode selector. Pick Ask and the agent reads, investigates, and answers questions about your project. Build is still the default and works exactly as before. Ask mode is strictly read-only. The agent can’t edit files, run commands, deploy, or change settings.
Also shipped Jul 30, 2026Netlify in July 2026 →
You can add tables, views, data sources, and data quality tests as tasks to BigQuery pipelines
You can add tables, views, data sources, and data quality tests as tasks to BigQuery pipelines. For more information, see Add a pipeline task . This feature is generally available .
You can audit when users download query results by using the BigQuery console
You can audit when users download query results by using the BigQuery console. Data Access audit logs for the tabledata.list method now include a uiDownloadRequest field to indicate whether the request was triggered by a UI download. This feature is generally available (GA).
Adaptive refresh mode for dynamic tables (General availability)
ADAPTIVE refresh mode for dynamic tables is now generally available. ADAPTIVE refresh uses incremental refresh by default but automatically reinitializes the dynamic table when internal heuristics detect that the volume of upstream changes makes an incremental refresh significantly more expensive than a full refresh.
Genie Agents enhancements and bug fixes
- Chat sharing : Sharing an individual Genie Agent conversation is now generally available. See Share a conversation . Download visualizations on Private Link (Beta) : You can now download visualization results through the Genie Conversation API on Private Link workspaces in supported regions. See the Conversation API reference .
More from NetlifyEvery Netlify release →
GPT-5.6 Luna and Terra price reduction on AI Gateway
GPT-5.6 Luna now costs 80% less and GPT-5.6 Terra is 20% less through Netlify AI Gateway, making both models more cost-efficient for production AI workloads. These reductions improve the price-performance tradeoff across the GPT-5.6 model family, giving teams more flexibility to choose the right balance of capability and cost for each workload.
Keep projects private by default with project visibility
Teams on a Free, Personal, or Pro plan now have project visibility settings to ensure that all of your project stay private until you decide to make them public. More people are shipping prototypes, internal tools, early client work, and projects built with agents. A deploy is often a work in progress, not a publication.
Netlify Drop updates
Netlify Drop has a refreshed look, with even more support for your questions and guidance on what’s next after you drop your latest site or app. We first launched Netlify Drop 13 years ago when we introduced the web to a simpler way to deploy your web project and get a custom link for it.
Security Update: Multiple vulnerabilities in Nuxt
The Nuxt team has disclosed several security vulnerabilities fixed in Nuxt 4.5.1 and 3.21.10, ranging from a high-severity server-side remote code execution (under specific conditions) to lower-severity and development-only issues. Here’s what Netlify customers need to know.
Claude Opus 5 Now Available in AI Gateway and Agent Runners
Anthropic’s Claude Opus 5 model is now available through Netlify’s AI Gateway and Agent Runners with zero configuration required. Use the Anthropic SDK directly in your Netlify Functions without managing API keys or authentication. The AI Gateway handles everything automatically.
AI Gateway adds OpenRouter support for more AI model choice
The AI Gateway now supports OpenRouter, giving you access to models from providers beyond Netlify's direct integrations (OpenAI, Anthropic, Google Gemini). This partnership opens up models from providers like DeepSeek, Meta, Mistral, Qwen, and xAI, all billed through your existing Netlify credits.
Agent Runners adds OpenCode and AI model controls
Through a new partnership with OpenRouter, you can now choose OpenCode as an AI agent with Agent Runners. OpenCode allows you to choose many different AI models, including Kimi, DeepSeek, and GLM. Learn more about our OpenRouter partnership through the Netlify blog on open models.
SolidStart 2 just works on Netlify
SolidStart 2 is out, and it deploys to Netlify with no framework-specific adapter to install, a first for full-stack frameworks on Netlify. While SolidStart 1 deployed to Netlify through Nitro under the hood, SolidStart 2 no longer includes Nitro, building directly on Vite’s Environment API instead.