Entity coverage
Every NG Tech LLC signal, daily brief, and feature tied to Vercel, grouped by publish date.
143 published items, page 1 of 3.
Archive
Every published piece for Vercel, newest first.
Vercel's AI Gateway now serves Z.ai's GLM 5.3 FlashX, letting developers call the model through a single API key at roughly 200 tokens per second, with automatic provider fallback…
Vercel expanded its Spend Management controls to Enterprise Flexible Commitment plans, letting those customers configure spending limits with alerts and automated deployment contr…
Vercel added experimental WebMCP support to mcp-handler, letting a site expose its existing MCP tools to in-browser agents by adding a single script tag. Developers opt tools in v…
Vercel's v0 can now install private npm and custom-registry packages using credentials stored as shared environment variables (NPM_TOKEN or NPM_RC), letting teams build in v0 with…
Harbor 0.22.0 can now run Terminal-Bench and other agent evaluations inside Vercel Sandbox microVMs, letting teams execute isolated benchmark runs on Vercel's ephemeral compute.
OpenAI's GPT-Live 1 is now available on Vercel AI Gateway, bringing full-duplex voice conversations with client-controlled delegation and per-second billing to apps routing throug…
The Vercel CLI can now deploy static artifacts to Vercel in under one second, cutting the latency between building output and having it live for fast iteration and automated pipel…
Vercel added per-deployment control over Turbo build machines, letting developers switch on faster build infrastructure only when a given deployment needs it while keeping standar…
Vercel's skills CLI now supports installing agent skills directly from Notion-hosted databases, removing the requirement that a skill live in a Git repository before it can be ins…
On September 15, 2026, Vercel made Google's Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking available through Vercel AI Gateway, enabling real-time audio conversations route…
On September 14, 2026, Vercel's AI SDK harness layer gained native subscription authentication: harnesses that support their own subscriptions can now authenticate through them, s…
On September 11, 2026, Vercel added access controls to Vercel Connect so Pro and Enterprise teams can restrict who is allowed to create and manage connectors, tightening governanc…
On September 10, 2026, Vercel added GitHub Copilot to the AI SDK harness layer via the @ai-sdk/harness-github-copilot adapter, which connects Copilot through the same HarnessAgent…
On September 10, 2026, Vercel documented building and deploying with OpenAI's Agents API on its platform, combining Next.js, Vercel Functions, Queues, and Sandbox to host long-run…
On September 10, 2026, Vercel made Tako Search, live web search usable by any model routed through Vercel AI Gateway, free through September 30, 2026, giving developers a no-cost…
In its September 10-11, 2026 changelog, Vercel expanded Vercel Sandbox, its isolated environment for running untrusted or agent-generated code, to all compute regions with per-san…
In its September 4, 2026 weekly update, Vercel added per-user budget controls to its AI Gateway and expanded model availability, including Claude Fable 5.1, Gemini 3.8 Flash, and…
On September 3, 2026, Vercel made Basic build machines generally available to Pro and Enterprise teams, offering a cheaper 2 vCPU / 8 GB compute tier aimed at smaller applications…
On September 3, 2026, Vercel added support for running Cursor Cloud Agents inside Vercel Sandbox. Each agent request executes in its own isolated Firecracker microVM, while Vercel…
Between September 1 and 2, 2026, Vercel AI Gateway onboarded a cluster of newly released frontier models — Google's Gemini 3.8 Flash, Alibaba's Qwen 3.8 Max 0902, Meta's Muse Spar…
Vercel added user-scoped budgets to AI Gateway (announced August 31, 2026), letting teams cap what each member spends across their API keys and app tokens. Budgets support default…
On August 28, 2026, Vercel introduced agent-building capabilities directly in its dashboard: a builder that scaffolds an agent's code, pushes it to the user's Git repo, and create…
On August 21, 2026, Vercel introduced always-on tracing that automatically collects sampled traces from production and preview traffic, letting teams debug real requests without r…
On August 21, 2026, Vercel introduced Deployment Storage billing, charging $0.10 per GB per month for new Pro and Enterprise teams. The change puts a metered price on the storage…
On August 21, 2026, Vercel made it possible for apps and agents built in v0 to securely connect to 100+ third-party services, including Slack, Google, Notion, GitHub, and Salesfor…
On August 20, 2026, Vercel added a --bypass-all-settings flag to `vercel ai-gateway api-keys create`. Keys created with it are exempt from every team restriction on the AI Gateway…
On August 20, 2026, Vercel added vercel vcr CLI commands to manage the Vercel Container Registry, including creating repositories and browsing images and tags, with support for Do…
On August 20, 2026, Vercel added a vercel comments command that lets developers list, inspect, reply to, and resolve Vercel Toolbar review comments directly from the terminal.
On August 20, 2026, Vercel made Bun 1.4 available in Vercel Functions; Bun 1.4 is a complete rewrite from Zig to Rust with improved Node.js compatibility and bug fixes.
On August 20, 2026, Vercel added support for custom metrics, letting developers emit their own metrics from Vercel Functions and analyze them alongside Vercel's built-in observabi…
On August 19, 2026, Algolia became available as a native integration in the Vercel Marketplace, letting teams add search and discovery to their applications without provisioning o…
On August 19, 2026, Vercel began letting Pro and Enterprise teams preview and download compliance attestations such as SOC 2 Type 2 and security policies directly from their team…
On August 19, 2026, Vercel added Fish Audio's speech and transcription models to the Vercel AI Gateway, accessible through a single API key with built-in spend monitoring and offe…
On August 19, 2026, Vercel Connect added Microsoft support that automatically handles Microsoft Entra app registration and can generate both delegated and application tokens, stre…
On August 19, 2026, Vercel launched Vercel for Slack in public beta, an integration that lets teams collaborate on coding, investigate production issues, and run approved remediat…
On August 19, 2026, Vercel added an Instagram adapter to its Chat SDK, letting developers build AI chat agents that operate in Instagram Direct Messages with support for media, qu…
On August 18, 2026, Vercel made Cline available in the AI SDK harness layer via the @ai-sdk/harness-cline adapter, built with the Cline team, letting developers drive the Cline co…
On August 18, 2026, Vercel for Platforms added support for provider-supplied short-lived GitHub tokens for deployments; Vercel encrypts and retrieves source code on demand without…
On August 18, 2026, Vercel introduced KMS (public beta), a managed key service that lets Vercel Functions sign JWTs and messages with managed keys while keeping private keys out o…
On August 18, 2026, Vercel added Z.ai's GLM-5.3 to its AI Gateway, callable with a single API key with no platform fee, automatic fallbacks, spend tracking, and per-request traces.
Vercel is discounting OpenAI's GPT-5.6 Sol by 50% on all requests routed through the Vercel AI Gateway from August 17 to September 18, 2026, announced in its August 18 changelog.
In mid-August 2026, Vercel added a harness layer to the AI SDK that lets developers run established coding-agent runtimes through a single unified interface, with support for any…
On August 13, 2026 Vercel announced that GLM 5.2, Z.ai's open-weights coding model with a 1M-token context window, is free for eve agents through August 27, served by Blackbox AI…
On August 13, 2026, Vercel made the v0 API generally available, letting developers invoke its AI app-building agent programmatically from their own products, scripts, CI pipelines…
On August 12, 2026 Vercel launched `vercel ai-gateway coding-agents setup`, a single command that auto-detects installed coding agents and reconfigures them to run through Vercel'…
Vercel added xAI's Grok Imagine Image 2.0 as a preview model on its AI Gateway on August 8, 2026, letting developers call the model as xai/grok-imagine-image-2.0-preview via gener…
On August 7, 2026 Vercel made its AI Gateway and Sandbox available inside Hermes Agent, giving the agent inference across 200+ models with no token markup and isolated microVM exe…
On August 7, 2026, Vercel introduced Skill Packs, which bundle multiple agent skills into a single shareable, unlisted URL built from community skills, local folders/zips, or publ…
Vercel's Chat SDK now ships a chat/workflow module where a single requestApproval call pauses a running Workflow SDK workflow and posts an Approve/Deny card until a person decides…
A cross-vendor standard called Agent Plugins 1.0, initiated by Vercel with a steering committee of Amazon, Anysphere (Cursor), Microsoft, and OpenAI plus GitHub, defines how agent…
Vercel added Meta's Muse Spark 1.2 to AI Gateway with bring-your-own-key support and no markup. The 1.2 update focuses on code generation, complex debugging, codebase understandin…
Vercel AI Gateway now produces an OpenTelemetry trace for every request, and Pro and Enterprise teams can stream those traces to any OTLP/HTTP endpoint via Vercel Drains. Traces c…
Vercel AI Gateway can now be purchased through AWS Marketplace, letting teams put inference spend on their AWS bill with private offers and usage-based pricing. Per-token cost is…
Vercel Sandbox now supports up to 10,000 concurrent sandboxes on Pro and Enterprise plans, up from 2,000, with per-minute vCPU allocation scaling automatically to 5,000. A dynamic…
Vercel introduced skill packs on skills.sh, letting developers bundle multiple agent skills into curated, shareable collections distributed as a single URL. Packs can be assembled…
Vercel shipped agent-browser, a new @agent-browser/eve extension that lets eve agents navigate the web like a human. Agents get tools for navigation, reading page content, clickin…
Vercel improved deploy performance for apps that use Incremental Static Regeneration (ISR), cutting deploy times by up to 33% for projects with many prerendered pages. The largest…
Vercel added cross-team sharing for Container Registry repositories, allowing a single repository to be shared with up to 100 Vercel teams. The change targets larger organizations…
Vercel made WAF for Blob generally available, letting teams protect Blob stores with WAF custom rules in production on all plans. The move extends Vercel's web application firewal…
Vercel's AI Gateway spend budgets, which cap cumulative dollar spend with email alerts at 50/75/100% and inherited defaults, now extend to individual team members: on August 31, 2…