# Vercel News Blog This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Hobby projects now retain fewer deployments to free up storage DevFeed: [Hobby projects now retain fewer deployments to free up storage]() Original publisher: [Read original article]() Author: Pranav Kanchi Published: 2026-09-16T18:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [Deployment](), [Disk image]() Tags: [3](), [deployments](), [retention](), [storage](), [upgrade]() ### AI overview Vercel has changed Deployment Retention for Hobby teams. Each Hobby project now keeps its three most recent production deployments and three most recent deployments of any type, while some protected deployments remain exempt. Deployments outside the exceptions are deleted immediately when a team exceeds the 10GB storage limit. ### Source excerpt Hobby projects now retain fewer deployments past the 30-day retention window. Hobby teams get 10GB of Deployment Storage. Every deployment you keep uses some of it, and going over the limit can block you from deploying until you free some up. Deployment Retention for Hobby teams now deletes old deployments sooner, so dormant projects stop holding storage that your active projects need. Each Hobby project now keeps its 3 most recent production deployments, plus its 3 most recent deployments of any type, regardless of age. Preview deployments no longer get their own protection. Your current production deployment is still never deleted, and aliased and active-branch deployments are still protected. See the full list of exceptions in the docs. If your team is over the 10GB limit, deployments outside those exceptions are now deleted immediately instead of after 30 days. To stay under the limit, see how to optimize your Deployment Storage usage, or upgrade to Pro, where storage is billed at $0.10 per GB per month. Read more ## Mem0 joins the Vercel Marketplace DevFeed: [Mem0 joins the Vercel Marketplace]() Original publisher: [Read original article]() Author: Tony Pan Published: 2026-09-16T17:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [Vercel](), [Artificial Intelligence](), [App](), [context](), [API keys](), [Command-line interface](), [Environment Variables]() Tags: [ai](), [ai-agents](), [app](), [billing](), [cli](), [context](), [environment-variables](), [free](), [giving](), [install](), [integration](), [vercel](), [volume]() ### AI overview Mem0 is now a native integration on the Vercel Marketplace, providing long-term memory for AI agents and apps across sessions. The integration includes billing through Vercel, automatic provisioning of a scoped Mem0 project and API key, and environment-variable configuration. Mem0 offers a free plan with usage limits and a $20-per-month plan for higher volume. ### Source excerpt Mem0 is now available as a native integration on the Vercel Marketplace, giving your AI agents and apps long-term memory. Mem0 remembers user preferences, facts, and context across sessions, so your app stops starting from scratch. Install from the Marketplace with integrated billing on your Vercel invoice, no separate account or key management. A scoped Mem0 project and API key are provisioned automatically and added to your project as environment variables, including MEM0_API_KEY. Mem0 offers a free plan with usage limits and a $20 per month plan for higher volume. To see it end to end, deploy the eve Memory Agent template, an eve agent with long-term memory powered by Mem0. Get started with Mem0 on the Vercel Marketplace or through the Vercel CLI, available to customers on all plans. Read more ## Secure Compute and Static IP builds start 64% faster DevFeed: [Secure Compute and Static IP builds start 64% faster]() Original publisher: [Read original article]() Author: Karim Hasebou Published: 2026-09-16T17:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [Deployment](), [Containers](), [Network Configuration]() Tags: [automatically](), [build](), [compute](), [containers](), [faster](), [ip](), [network-configuration](), [static]() ### AI overview Vercel reports that builds using Secure Compute or Static IPs now start 64% faster on average, improving from 6.7 seconds to 2.4 seconds. The change uses prewarmed build containers with network configuration attached at build start and requires no configuration changes. ### Source excerpt Builds using Secure Compute or Static IPs now start 64% faster, with the average time from deployment creation to build start dropping from 6.7 seconds to 2.4 seconds. Previously, each build waited for a new build container to boot with its network configuration. These builds now use prewarmed build containers, with your network configuration attached when the build starts. The improvement is applied automatically to builds using Secure Compute or Static IPs, with no configuration changes required. Learn more about Secure Compute and Static IPs. Read more ## TypeSafe AI's Jev now available on AI Gateway DevFeed: [TypeSafe AI's Jev now available on AI Gateway]() Original publisher: [Read original article]() Author: Jerilyn Zheng Published: 2026-09-16T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [gateway](), [SDKs](), [API](), [Software]() Tags: [ai-gateway](), [api](), [evaluation](), [gateway](), [model](), [queue](), [retry](), [sdk](), [software](), [support](), [typesafe-ai]() ### AI overview Vercel's AI Gateway now supports TypeSafe AI's Jev, a probabilistic decision model that returns typed Choice, Score, and Boolean answers with probabilities. The changelog describes parallel evaluation, AI SDK 7 integration through an experimental evaluate API, example routing and review workflows, and provider options including Zero Data Retention and No Training. ### Source excerpt Jev from TypeSafe AI is now available on AI Gateway. Jev is a probabilistic decision model for software: state goes in, typed Choice, Score, and Boolean answers come out. Regular language models generate text one token at a time, which the application then parses and validates. Jev evaluates all declared questions in parallel and returns typed answers plus probabilities directly. That removes unnecessary text generation and makes it straightforward to automate clear cases while routing uncertain ones to review. TypeSafe reports Jev was up to 193.6x faster and 444.6x cheaper than LLMs on its workflow evaluations. Example use cases include: Choosing the next tool or subagent in an agent loop Deciding whether to continue, retry, ask the user, or stop Scoring urgency or risk before an action Verifying model outputs and enforcing guardrails. AI SDK 7 exposes Jev through the experimental evaluate API. Choice selects an option, Score grades an ordered rubric, and Boolean estimates the probability of true. Install the current AI SDK (AI SDK 7.0.105 onwards supports the evaluate API): Each evaluation specifies: model: the evaluation model to call, state: the shared string, object, or array to evaluate, and questions: a map of named decisions to make about that state. Call the model with typesafe-ai/jev. This example turns one support case into a queue, priority, and refund-review decision, with uncertain routing sent for manual review: The result preserves question IDs and Choice keys. TypeSafe reports separate Choice and Score confidence in result.providerMetadata.typesafe.confidence. Calibrate probabilities and confidence against labeled examples from your workflow. Jev supports Zero Data Retention and No Training, enabled per request in the example. Evaluation calls also appear in logs and custom reporting, count toward budgets, and accept other Gateway provider options in the same providerOptions.gateway object. Read the documentation on evaluation models on AI Gateway f ## Is Agentic now tailors its audit by site type DevFeed: [Is Agentic now tailors its audit by site type]() Original publisher: [Read original article]() Author: Rich Haines Published: 2026-09-16T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [audit](), [App](), [API](), [Authentication](), [Error Handling](), [SDKs]() Tags: [api](), [app](), [audit](), [authentication](), [error-handling](), [sdk]() ### AI overview Is Agentic reports now support four site-type views: Docs & content, Business, App, and Commerce. The selected view changes which checks are highlighted, while scores remain comparable and unchanged. ### Source excerpt Is Agentic reports now let you view your checks through one of four site types: Docs & content, Business, App, or Commerce. For example, the Commerce view highlights payment and checkout standards like x402, UCP, and ACP, while the App view highlights API discovery, authentication, error handling, and SDK support. Your score stays the same in every view, and you can change views on an existing report without rescanning. Only the highlighted checks change, so you can focus on what matters for your kind of site while keeping scores comparable across sites. To set the default view, add a single meta tag to your page's : Set the value to match your site type: content for Docs & content business for Business app for App store for Commerce The tag only sets which view readers see first. It doesn't add points or change your score. If no type is declared, Is Agentic infers one and shows which type it chose. Run a check at is-agentic.com or read the documentation. Read more ## How Delphi ships 100 times a day with its Python backend on Vercel DevFeed: [How Delphi ships 100 times a day with its Python backend on Vercel]() Original publisher: [Read original article]() Author: Kevin Sundstrom Published: 2026-09-15T04:00:00Z Content type: article Language: en Sources: [Vercel News]() Topics: [Python](), [Vercel](), [Back end](), [feature flags](), [Amazon Web Services](), [Docker](), [airflow]() Tags: [aws](), [backend](), [docker](), [feature-flags](), [python](), [vercel](), [workflow](), [workflows]() ### AI overview A Vercel case study describes how Delphi rebuilt its Python backend on Vercel after previously using AWS, ECS, Docker Desktop, and local databases. The move gave the team a shared deployment workflow, faster onboarding, and more than 100 production deploys per day, while Vercel Workflows and Queues support long-running work and background jobs. ### Source excerpt Delphi on Vercel 10 engineers with no dedicated infrastructure role Everyone ships code, including product and design 100+ production deploys a day behind feature flags Delphi builds digital minds. They capture what someone has written, recorded, and taught, so anyone can tap that expertise on demand. Delphi is "a destination where you can find and interact with interesting minds," says founding engineer Spencer Schoeben. Nobody has built a digital mind network before, so Delphi figures out what to build by shipping features and watching how people use them. That only works if the product is fast to change. "If we are going to win, we need to have an excellent developer and agentic experience," Spencer says. "Otherwise, we could not adapt to how fast our user's demands change." Delphi's frontend had run on Vercel since day one. "The frontend has always been easy," Spencer says, "but the backend was a nightmare." Six months ago, the team rebuilt its Python backend on Vercel as well. Today the whole team ships to production 100+ times a day. Building a Python backend that's easy to work onThe backend slowed every change Delphi's backend previously ran on AWS, with ECS, Docker Desktop, and local databases. In the earliest days, the setup worked because the team was small and much of the context lived in people's heads. As Delphi grew, that made onboarding slower than the team wanted: getting a new engineer to their first deploy took a full day of environment setup. Delphi could have fixed that without leaving AWS. But fixing it properly would have meant designing and owning the infrastructure themselves, and the team didn't want to own infrastructure at all. "That is not our current goal as a company," Spencer says. After moving the backend to Vercel, new engineers could get to production much faster, with the same deploy workflow the rest of the team used every day. Workflows and Queues made the move possible When Delphi was founded, Vercel Workflows and Vercel Queues ## Gemini 3.8 Live models now available on AI Gateway DevFeed: [Gemini 3.8 Live models now available on AI Gateway]() Original publisher: [Read original article]() Author: Jerilyn Zheng Published: 2026-09-15T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [real-time](), [Artificial Intelligence](), [API](), [Google](), [WebSocket](), [SDKs]() Tags: [ai](), [api](), [cost](), [failover](), [gemini](), [google](), [real-time](), [realtime](), [sdk](), [websocket]() ### AI overview Vercel announces that Google's Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking models are available on AI Gateway. The models support real-time spoken interactions, audio and visual grounding, multilingual switching, background tool calls, and parallel reasoning through the AI SDK's realtime API. ### Source excerpt Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking from Google are now available on AI Gateway. Both models support real-time spoken interactions for voice assistants, conversational experiences, and applications that respond through audio. google/gemini-3.8-live supports real-time audio, visual grounding, automatic switching across 97 languages, and background tool calls while the conversation continues. google/gemini-3.8-live-extended-thinking adds multi-step reasoning that runs in parallel with speech, allowing it to acknowledge requests and narrate progress without interrupting the conversation. Use either model through the AI SDK's realtime API. Install the Gateway provider and a WebSocket client: Mint a short-lived token, open the WebSocket, and use the model adapter to serialize and parse realtime events: See the realtime quickstart for more details on realtime events and WebSocket connections. Try Gemini 3.8 Live or Gemini 3.8 Live Extended Thinking in the model playground. AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. Read more ## AI SDK harness layer now supports native subscription authentication DevFeed: [AI SDK harness layer now supports native subscription authentication]() Original publisher: [Read original article]() Author: Felix Arntz Published: 2026-09-14T21:28:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [vercel ai sdk](), [Authentication](), [OAuth](), [codex](), [Claude Code]() Tags: [ai](), [authentication](), [claude-code](), [codex](), [coding-agents](), [copilot](), [cursor](), [gateway](), [oauth](), [opencode](), [sdk]() ### AI overview The AI SDK harness layer now supports authenticating supported coding-agent harnesses through their native subscriptions. It uses explicit provider credentials when available, otherwise falls back to a host-native subscription without requiring code or configuration changes. ### Source excerpt The AI SDK harness layer now supports authenticating harnesses through their native subscriptions, where the underlying harness supports them. The harness layer runs different coding agents through the same HarnessAgent interface, so you can switch agents without changing your application code. No code changes or new settings are required. The direct authentication mode uses explicit provider environment credentials when they are present, and otherwise a native subscription found on the host. The default auto mode does the same when no AI Gateway credentials are set. The ai-gateway mode never reads native subscriptions. Native subscription credentials stay on the host. Just like with API keys, credentials are resolved at the host boundary. OAuth access tokens are refreshed there as needed. Where the sandbox supports it, the harness receives placeholder credentials and the real token is injected into outbound requests on the host. Native subscriptions work across harness adapters wherever the harness itself supports subscription login. These include Claude Code, Cline, Codex, Cursor, fx, GitHub Copilot, Grok Build, OpenCode, and Pi. Read the harness documentation to learn more. Read more ## Vercel Sandbox now provides 64 GB of storage DevFeed: [Vercel Sandbox now provides 64 GB of storage]() Original publisher: [Read original article]() Author: Luke Phillips-Sheard Published: 2026-09-11T06:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [Vercel]() Tags: [agent](), [dependencies](), [documentation](), [sandbox](), [sandboxes](), [storage](), [vercel]() ### AI overview Vercel Sandbox storage has increased from 32 GB to 64 GB for all sandboxes, including those created from managed or custom images and those using the deprecated runtime property. ### Source excerpt Every Vercel Sandbox now includes 64 GB of storage, up from 32 GB. This includes sandboxes created from a Vercel Managed Image or custom image, as well as those configured with the deprecated runtime property. The additional space provides more room for large repositories, dependencies, build artifacts, data workloads that spill to disk, and storage-intensive agent tasks. Learn more about Sandbox images in the documentation. Read more ## How Tailscale built a customer-facing model router on AI Gateway DevFeed: [How Tailscale built a customer-facing model router on AI Gateway]() Original publisher: [Read original article]() Author: Susan Aziz Published: 2026-09-11T04:00:00Z Content type: article Language: en Sources: [Vercel News]() Topics: [AI Platform](), [networking](), [API keys]() Tags: [ai-gateway](), [ai-models](), [api](), [model-routing](), [sandbox](), [security](), [vercel]() ### AI overview Tailscale describes using Vercel AI Gateway and Sandbox to deliver customer-facing access to hundreds of AI models through tailnet identity. The article explains that provider integration and secure agent execution were complex enough that Tailscale chose managed routing and sandboxing instead of building those layers in-house. ### Source excerpt Tailscale on Vercel Hundreds of AI models shipped to customers in-product Model access granted and revoked by tailnet network identity Went from model routing prototype to paying customers in months Tailscale connects a company's laptops, servers, cloud instances, and personal devices into one private network called a tailnet. Remy Guercio, who leads product for Aperture by Tailscale, describes it simply: "It's basically like a VPC that can span any cloud, on-prem, your house, and your phone." Aperture takes that same idea and applies it to AI. Instead of giving every employee, agent, or tool a separate provider API key, Aperture lets companies control model access through the tailnet itself. Add someone to the network, and they can immediately use approved models. Remove them, and access disappears. Under the hood, Aperture is built on Vercel AI Gateway and Vercel Sandbox. AI Gateway gives Tailscale one API for hundreds of models. Sandbox gives agents a safe place to run. Together, they let Tailscale offer model access and agent execution inside a customer's private network, without their team building every piece of AI infrastructure from scratch. Model routing is harder than it looks Tailscale is an infrastructure company, so building the routing and execution layers in-house was the obvious first option. But once they took a deeper look into the engineering effort required, they chose not to. The provider layer looked deceptively simple from the outside. "You would think all of the endpoints are the same," Remy says. "They are not." David Carney, Co-founder and Chief Strategy Officer, has the receipts, because Tailscale still maintains that plumbing for a few customers who haven't migrated to Aperture yet. "There are a lot of things the big providers don't do that blow my mind that the gateway does, like simply putting the cost in the response," he says. "We initially built those systems for customers ourselves, and the complexity is insane." Agents raised the s ## How Featured's users make 100K media pitches per month on Vercel DevFeed: [How Featured's users make 100K media pitches per month on Vercel]() Original publisher: [Read original article]() Author: Susan Aziz Published: 2026-09-11T04:00:00Z Content type: article Language: en Sources: [Vercel News]() Topics: [migration](), [vercel ai sdk](), [AI Chat](), [SDKs]() Tags: [ai](), [ai-gateway](), [aws](), [featured](), [infrastructure](), [migration](), [models](), [vercel](), [vercel-ai-sdk](), [workflow]() ### AI overview Featured describes migrating 374 Sanity sites from AWS Elastic Beanstalk to Vercel while using Vercel's AI SDK, AI Gateway, and Workflow SDK to reduce infrastructure work for a three-engineer team. ### Source excerpt Featured on Vercel 3 engineers supporting 3 brands and 100,000+ users on Vercel Migrated 374 Sanity sites from AWS Elastic Beanstalk to Vercel AI SDK and AI Gateway power Featured's chat bot across 17 models Workflow SDK replaced custom long-running job infrastructure Featured is a co-pilot for public relations (PR) that subject matter experts and PR teams use to find media opportunities. Tell Featured's agents what you know, and it surfaces opportunities across journalist requests, podcasts, awards, and GEO, with no PR background required. Founder Brett Farmiloe knows from experience how hard and time consuming getting press is. He spent 10 years running Markitors, a digital marketing agency with 500 small business clients. Every client, from an eyelash extension supplier to an equipment financing company, had real expertise to share, but no way to get it in front of journalists. PR, as Farmiloe puts it, "has always been about who has access to what." He founded Featured to change the question from who has access to who has knowledge. Featured connects one of their users with a journalist or publisher every 6 seconds. Their agents deliver more than 100,000 media pitches per month, and have sent over 100 million Help A Reporter Out (HARO) emails in the past year. Behind it all is an engineering team of just three people. With a team that lean, there's no time to manage servers or piece together custom integrations. Every hour spent on infrastructure is an hour taken away from building features what will help their customers land more media placements. The cost of managing infrastructure by hand Before Vercel, Featured's infrastructure work pulled the team away from product development. Hosting lived on AWS Elastic Beanstalk, AI features depended on custom provider integrations, and long-running, multi-step jobs ran on separate orchestration infrastructure. Each layer worked, but each one added operational overhead for a three-person team supporting multiple brands. ## Control who can manage connectors in Vercel Connect DevFeed: [Control who can manage connectors in Vercel Connect]() Original publisher: [Read original article]() Author: Allen Zhou Published: 2026-09-11T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [Vercel](), [Authorization]() Tags: [agents](), [connectors](), [documentation](), [enterprise](), [vercel]() ### AI overview Vercel Connect now lets Pro and Enterprise teams restrict connector management to Owners and users with the Connector Manager extended permission. Connectors provide applications and agents with access to external services through team-managed credentials. ### Source excerpt Pro and Enterprise teams can now control who can create and manage Vercel Connect connectors. Connectors let applications and agents access external services using credentials managed by your team. Owners can enable this restriction under Connector Permissions in Team Settings. Once enabled, only people with the Owner role or Connector Manager extended permission can create or manage connectors. Browse all connectors, or learn more in the Vercel Connect documentation. Read more ## GitHub Copilot is now available in the AI SDK harness layer DevFeed: [GitHub Copilot is now available in the AI SDK harness layer]() Original publisher: [Read original article]() Author: Felix Arntz Published: 2026-09-10T17:39:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [GitHub Copilot](), [vercel ai sdk](), [AI-assisted coding](), [cursor]() Tags: [agent](), [ai](), [claude](), [claude-code](), [code](), [codex](), [coding](), [copilot](), [cursor](), [github](), [github-copilot]() ### AI overview The AI SDK harness layer adds official GitHub Copilot support through an adapter, allowing applications to run Copilot and other coding agents through the same HarnessAgent interface. ### Source excerpt The AI SDK harness layer now supports GitHub Copilot through the official @ai-sdk/harness-github-copilot adapter. The harness layer lets your application run different coding agents through the same HarnessAgent interface, so you can switch agents without changing your application code. Pass githubCopilot to HarnessAgent: Under the hood, the adapter uses @ai-sdk/harness-acp to connect GitHub Copilot to HarnessAgent through the Agent Client Protocol (ACP). Supported harnesses now include, in addition to GitHub Copilot, Claude Code, Cline, Codex, Cursor, Deep Agents, fx, Grok Build, OpenCode, and Pi, with more coming soon. Read the GitHub Copilot harness documentation to get started. Read more ## FastAPI frontends and static files served from the CDN DevFeed: [FastAPI frontends and static files served from the CDN]() Original publisher: [Read original article]() Author: Daniel Park Published: 2026-09-10T17:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [FastAPI](), [Vercel](), [Front end](), [mount]() Tags: [cdn](), [frontend](), [mount](), [tool](), [vercel]() ### AI overview Vercel now promotes FastAPI frontends and static files served through app.frontend() or StaticFiles to the Vercel CDN at build time, allowing matching requests to bypass Vercel Functions. Route precedence is preserved, while dependency-protected frontends and middleware-protected static files remain on the function unless configured otherwise. ### Source excerpt FastAPI frontends and static files, served with app.frontend() or StaticFiles, are now promoted to the Vercel CDN at build time. Requests for those paths are served directly from the CDN, without invoking your Vercel Function. FastAPI evaluates routes in declaration order. A route declared before a StaticFiles mount takes priority over any CDN file at that path. This precedence is preserved. Promoted source directories remain in the function bundle so the app can read from them at runtime. To exclude them and serve only from the CDN, set tool.vercel.fastapi.static.exclude = true in pyproject.toml. Frontends guarded by dependencies are kept on the function as the CDN cannot run dependency checks. Similarly, static files which sit behind middleware are also kept on the function. To override this and always promote to CDN, set tool.vercel.fastapi.static.cdn = true. To opt out of the CDN entirely, set it to false instead. For more information see the Vercel FastAPI documentation. Read more ## How we cut CDN metadata lookup latency by 91% DevFeed: [How we cut CDN metadata lookup latency by 91%]() Original publisher: [Read original article]() Author: Luba Kravchenko Published: 2026-09-10T00:00:00Z Content type: article Language: en Sources: [Vercel News]() Topics: [Latency](), [Vercel](), [Caching](), [Routing (disambiguation)](), [API](), [React Native]() Tags: [api](), [cache](), [cdn](), [deployment](), [latency](), [routing](), [vercel]() ### AI overview Vercel describes how it reduced P99 CDN metadata lookup latency by 91%. The team replaced per-path metadata fetching with bounded shards that group metadata for many paths, improving cache reuse across routing lookups while controlling data-fetching costs. The article also explains how framework routing rules, Build Output API outputs, Bloom filters, and exact metadata lookups work together to select the correct response. ### Source excerpt Every request to Vercel passes through our CDN, which executes on average over 80 million routing instructions per second. Part of that work is looking up metadata to determine which paths exist and how to serve them. When that metadata isn't cached, the CDN has to fetch it before it can serve the response. We used to fetch and cache metadata one path at a time, retrieving only what each lookup needed. That seemed efficient at the time, but large deployments can contain hundreds of thousands of paths, each with its own cache entry. Every new deployment introduced fresh metadata, making cache misses a recurring cost for large sites that deployed frequently. Fetching more metadata at once made these lookups faster. By grouping paths together, each fetch could populate the cache for many subsequent lookups. But fetching too much introduced its own costs. Through production experiments, we found a balance that cut P99 metadata lookup latency by 91% and made deployments faster along the way. How the CDN finds the right route The path in a request doesn't always match the path of the content or function that serves it. Framework routing rules connect the two. A request for /blog/hello-world, for example, might resolve to the dynamic route /blog/[slug]. A request for that page's React Server Component payload might resolve to /blog/[slug].rsc. As the CDN applies these rules, it may need to check several target paths to find the right response. The framework describes those routes during a build. With framework-defined infrastructure, application code declares which outputs are static, which need Functions, and which responses can be cached or regenerated. Frameworks translate that intent into Build Output API outputs, and Vercel generates the routing metadata the CDN reads. At request time, the CDN needs to determine which target paths exist and retrieve their metadata. The Bloom filters we added to global routing rule out paths that definitely don't exist. Remaining paths ## Tako Search is free on AI Gateway through September 30 DevFeed: [Tako Search is free on AI Gateway through September 30]() Original publisher: [Read original article]() Author: Jerilyn Zheng Published: 2026-09-10T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [vercel ai sdk](), [SDKs](), [API](), [Web](), [data]() Tags: [ai](), [ai-gateway](), [api](), [configuration](), [documentation](), [free](), [integration](), [playground](), [sdk](), [search](), [tools](), [web]() ### AI overview This changelog announces that Tako Search is free on AI Gateway through September 30. It enables AI models to search curated data and the live web, filter results, and provide current answers with citations and visualizations. Tako Search works with any model on AI Gateway and does not require a separate Tako account or API key. ### Source excerpt Tako Search is free exclusively on AI Gateway through September 30. It lets AI models search Tako's curated data and the live web, filter web results by domain or publication date, and use the results to answer questions with current information, citations, and visualizations. After September 30, searches are billed at standard rates. The same integration works with any model on AI Gateway, so you can switch models without changing your search setup. You also don't need a separate Tako account or API key. To use Tako Search with the AI SDK, add gateway.tools.takoSearch() to a generateText or streamText request. The model can then call it when it needs current information: Try Tako Search in the AI Gateway playground. See the web search documentation for configuration and search options. Read more ## Build with OpenAI Agents API on Vercel DevFeed: [Build with OpenAI Agents API on Vercel]() Original publisher: [Read original article]() Author: Allen Zhou Published: 2026-09-10T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [AI Bots]() Tags: [agent](), [agents](), [api](), [architecture](), [code](), [guide](), [integration](), [openai](), [sandbox](), [scale](), [tool](), [vercel]() ### AI overview Vercel now supports building and deploying long-running, tool-using agents with the OpenAI Agents API. OpenAI manages agent loops and session state, while Vercel provides hosted applications, Sandbox execution, persistent workspaces, webhook and queue integration, and scale-to-zero operation. ### Source excerpt You can now build and deploy long-running, tool-using agents with the OpenAI Agents API on Vercel. OpenAI manages the agent loop and session state, while Vercel hosts the application and connects each session to Vercel Sandbox for code execution and file access. With this integration, you get: An OpenAI-managed agent loop and session state Reliable Sandbox creation and reconnection through signed OpenAI webhooks and Vercel Queues An isolated execution environment for every agent session A persistent workspace that retains files across follow-up instructions A scale-to-zero architecture without an always-on worker Follow the step-by-step guide to build and deploy an agent, or explore the sample application. Read more ## Vercel Sandbox is now available in all regions DevFeed: [Vercel Sandbox is now available in all regions]() Original publisher: [Read original article]() Author: Rob Herley Published: 2026-09-10T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [Vercel](), [cloud-infrastructure](), [Latency](), [Command-line interface](), [SDKs](), [configuration]() Tags: [cli](), [compute](), [configuration](), [cpu](), [enterprise](), [latency](), [memory](), [sdk](), [support](), [update](), [vercel]() ### AI overview Vercel Sandbox is now available across all 20 Vercel compute regions, expanding from four. Users can select primary and failover regions, helping reduce latency and meet data residency requirements. Region selection is available on every plan, while Pro and Enterprise teams can configure failover regions. ### Source excerpt Vercel Sandbox can now run in all 20 Vercel compute regions, up from four. Running sandboxes closer to the databases, storage, and other services they access reduces latency. Teams can also keep sandbox workloads in approved regions to support data residency and regional processing requirements. iad1 remains the default region. Region selection is available on every plan. Pro and Enterprise teams can also configure failover regions. If Vercel can't create a sandbox in the primary region, it tries each configured failover region in order. Teams with data residency requirements can limit primary and failover regions to approved geographies. Set a default region for new sandboxes from your project's Settings > Sandboxes. With the SDK: With the CLI: A region passed at creation overrides the project default. Existing sandboxes remain in the regions where they were created. Active CPU and Provisioned Memory rates vary by region. See Sandbox pricing. If you use the Sandbox SDK or CLI, update it to the latest version before selecting one of the newly supported regions. Learn about region selection, failover, and CLI configuration in the Sandbox regions documentation. Read more ## Password Protection is now available per project on Pro DevFeed: [Password Protection is now available per project on Pro]() Original publisher: [Read original article]() Author: Jas Garcha Published: 2026-09-09T06:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [passwords]() Tags: [deployment](), [security]() ### AI overview Pro teams can enable Password Protection for individual projects for $20 per project per month, replacing the previous $150-per-month team-level add-on option. ### Source excerpt Pro teams can now enable Password Protection for individual projects at $20 per project per month. When enabled, Password Protection requires visitors to enter a password you set before they can view the project's deployments. Open Security in the sidebar, select Deployment Protection, and turn it on. Disable it to stop future charges for that project. Previously, Password Protection was available only through a $150-per-month team-level add-on that covered every project. Learn more about Deployment Protection usage and pricing in the documentation. Read more ## Protect production deployments for free on every plan DevFeed: [Protect production deployments for free on every plan]() Original publisher: [Read original article]() Author: Jas Garcha Published: 2026-09-09T06:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [Vercel](), [Deployment](), [Authentication](), [Security](), [dashboards](), [Low-Code / Internal Tools]() Tags: [authentication](), [dashboards](), [deployment](), [internal-tools](), [password](), [security](), [vercel]() ### AI overview Vercel now lets every plan protect all project deployments, including production, with Vercel Authentication at no extra cost. The update also makes deployment protection exceptions free and lets Pro teams enable password protection per project. ### Source excerpt Vercel Authentication can now protect all deployments in a project, including production, at no additional cost on every plan. Previously, protecting production domains required the $150-per-month Advanced Deployment Protection add-on. When enabled, visitors must sign in with a Vercel account that has access to the project. This makes it useful for internal tools, private dashboards, and sites that aren't yet ready to launch. From your project, open Security in the sidebar, select Deployment Protection, then choose All Deployments from the dropdown. You can also make this the team default, so every new project starts with Vercel Authentication enabled for all deployments. With this change: Deployment Protection Exceptions are now free on every plan. Use an exception to make a specific preview domain public while keeping the rest of the project protected. Pro teams can now enable Password Protection for individual projects instead of purchasing it for the entire team. Learn more in the Deployment Protection documentation. Read more ## Persistent memory for eve agents DevFeed: [Persistent memory for eve agents]() Original publisher: [Read original article]() Author: Andrew Barba Published: 2026-09-09T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [Vercel](), [cloud-infrastructure]() Tags: [agents](), [memory](), [storage](), [tools](), [vercel]() ### AI overview eve agents can now retain context across sessions through persistent memory organized into named slots. Each slot defines a memory provider and sharing scope, with support for per-user memory, automatic or tool-driven updates, Vercel Blob storage, several external providers, and custom providers. ### Source excerpt eve agents can now retain context across sessions and use it in future conversations. Persistent memory is organized into slots. You can define named slots in files under agent/memory/. Each slot specifies a provider, which stores and retrieves the memory, and a scope, which determines who or what shares it. For example, you can keep separate memory for each authenticated user. Before each turn, eve retrieves relevant memory and adds it to the model's context. Depending on the provider, memory can be updated automatically after a turn, through tools the agent uses, or through both methods. To add eve's built-in file memory provider, run: The command creates a file memory slot scoped to each authenticated caller: For agents deployed on Vercel, file memory uses a private Vercel Blob store so saved memories persist across restarts and deployments. Other supported memory providers include Supermemory, Upstash AgentKit, and Kybernesis Arcana. You can also connect another storage system or memory service by building a custom provider. Read the memory documentation to choose a provider and get started. Read more ## v0 adds one-click integrations for email, auth, search, and databases DevFeed: [v0 adds one-click integrations for email, auth, search, and databases]() Original publisher: [Read original article]() Author: Jathin Singaraju Published: 2026-09-09T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [AI Chat]() Tags: [agent-skills](), [auth](), [code](), [databases](), [integration](), [react](), [search](), [skills](), [vercel]() ### AI overview Vercel's v0 adds inline Marketplace integrations for providers including Resend, Amazon OpenSearch, MongoDB Atlas, Algolia, and Clerk. Connected providers can be configured automatically, and provider skills can guide generated code. ### Source excerpt We're working toward bringing parity across Vercel integration and v0, starting with Resend, Amazon OpenSearch, MongoDB Atlas, Algolia and Clerk. Prompt v0 with what you want to build, and when your prompt requires a provider, v0 renders a connect card in the chat. With Marketplace integrations in v0, you get: Connect as you build: Prompt v0 with what you want to create, and connect the required provider inline. Automatic setup: Once connected, v0 handles the required environment variables and configuration. Provider skills loaded automatically: When you connect a provider that publishes agent skills, v0 loads them and generates code that follows the provider's recommended patterns. Provider-specific capabilities: Resend, for example, adds transactional email with React Email components. To get started, open a v0 chat and prompt what you want to add to your stack. Read more ## DeepSeek V4.1 Flash now available on AI Gateway DevFeed: [DeepSeek V4.1 Flash now available on AI Gateway]() Original publisher: [Read original article]() Author: Jerilyn Zheng Published: 2026-09-09T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [deepseek](), [Artificial Intelligence](), [API](), [Language models](), [AI-assisted coding](), [Claude Code](), [codex](), [cursor]() Tags: [ai](), [ai-gateway](), [api](), [caching](), [codex](), [context-window](), [cursor](), [deepseek](), [responses](), [tool](), [vercel](), [vision]() ### AI overview DeepSeek V4.1 Flash is now available through Vercel's AI Gateway, offering native image understanding, a 1 million token context window, responses up to 384,000 tokens, reasoning, tool use, and prompt caching. Developers can use it in Claude Code, Codex, Cursor, and other coding agents with the model name deepseek/deepseek-v4.1-flash. ### Source excerpt DeepSeek V4.1 Flash is now available on AI Gateway with native image understanding. V4.1 Flash has vision support and accepts text and images in the same request, so you can ask questions about screenshots, read charts, and extract information from visual content. The model has a 1 million token context window and supports responses up to 384,000 tokens, along with reasoning, tool use, and prompt caching. Its new architecture processes input and generates output with separate components, reducing the active computation needed for each stage. Use deepseek/deepseek-v4.1-flash as the model name: To use it in Claude Code, Codex, Cursor, and more, install the latest Vercel CLI and run setup: Then select deepseek/deepseek-v4.1-flash in the agent. See the coding agents guide for details. Try DeepSeek V4.1 Flash in the model playground. AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting, Zero Data Retention support, budgets for API keys, routing rules, and more. AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests. You can view all language models available on AI Gateway. Read more ## You can now read and search changelogs from the CLI DevFeed: [You can now read and search changelogs from the CLI]() Original publisher: [Read original article]() Author: Melkey Moksyakov Published: 2026-09-09T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [Command-line interface](), [changelog](), [Vercel](), [Terminal](), [AI-assisted coding](), [JSON](), [Markdown]() Tags: [agents](), [changelog](), [cli](), [coding-agents](), [content](), [features](), [json](), [markdown](), [products](), [search](), [terminal](), [update](), [vercel]() ### AI overview Vercel introduces the vercel changelog command for reading and searching Vercel changelog entries from a terminal. It supports result limits, keyword searches, full Markdown content, and JSON output for scripts and coding agents. The feature requires Vercel CLI 59.6.0 or later. ### Source excerpt You and your agents can now read and search the Vercel changelog feed from your terminal using vercel changelog. Coding agents can use this command to discover new Vercel products and features, find updates relevant to your project, and read full announcements to inform their recommendations. vercel changelog returns the latest five changelogs with full Markdown content. You can also set the number of results, search all changelogs using a keyword, and access JSON output for scripts and agents. Update the Vercel CLI to version 59.6.0 or later and run vercel changelog to get started. See vercel changelog --help for all available options. Read more [Next page]()