Chat SDK adds Kapso support
Chat SDK has added support for Kapso, a platform that connects bots to WhatsApp, through a new vendor-official adapter. The integration handles WhatsApp Business setup and webhooks, allowing developer…
Chat SDK has added support for Kapso, a platform that connects bots to WhatsApp, through a new vendor-official adapter. The integration handles WhatsApp Business setup and webhooks, allowing developer…
Vercel has launched WebSocket support in public beta for its Functions, enabling bidirectional communication for realtime features like AI streaming and chat. The WebSocket connections run on Fluid co…
Sakana AI released Fugu Ultra, a model that coordinates multiple frontier models to produce answers, now available on Vercel's AI Gateway. The model matches capabilities of Claude Mythos Preview and F…
Workflow SDK 5 beta now compresses run, hook, and step inputs and outputs using zstd, reducing storage and improving performance. Compression automatically applies to larger payloads, cutting storage …
Vercel launched The Agent Stack, a suite of tools including AI SDK, AI Gateway, Workflow SDK, and Vercel Sandbox, to help developers build production-grade AI agents without vendor lock-in. The stack …
At Vercel Ship 2026 in London, Vercel unveiled new agentic infrastructure including the Agent Stack, Vercel Connect, and the open-source agent framework eve, positioning itself as the platform for bui…
Vercel released Eve, an open-source framework for building AI agents using a directory-based approach where agents are defined with Markdown instructions, TypeScript tools, and deployable workflows. T…
Vercel has launched eve, an open-source agent framework for building, running, and scaling AI agents with built-in production features like durable execution, sandboxed compute, and human-in-the-loop …
Vercel announced Vercel Connect, a new service in public beta that replaces long-lived provider tokens with runtime credential exchange for agent access. The system uses short-lived, scoped credential…
Vercel released eve, an open-source framework for building, running, and scaling agents, now in public preview. The framework treats an agent as a directory of files with built-in production features …
Vercel removed CLI-specific deployment limits, enabling faster deployments from local machines and external CI/CD pipelines with instant feedback. Teams and AI agents can now deploy at the pace their …
Vercel launched Vercel Connect, a service that allows apps and AI agents to securely access external services like Slack, GitHub, and Salesforce using scoped, short-lived tokens instead of long-lived …
Vercel launched Enterprise Apps and Agents, a platform that enforces security and access controls for internal AI applications and agents, including identity-based authentication, short-lived credenti…
Vercel increased the maximum execution duration for Functions using Node.js and Python runtimes to 30 minutes for Pro and Enterprise teams, more than doubling the previous 800-second limit. The update…
Access to Claude Fable 5 has been suspended on AI Gateway for all users in compliance with a US Government directive. Anthropic has not indicated if or when access to the model will be restored, thoug…
Claude Design exports projects as .zip files, and Vercel Drop deploys those .zip files directly by dragging them into a browser without requiring unzipping, Git, or additional tooling. The pairing all…
Moonshot AI's Kimi K2.7 Code, a coding model designed for long-horizon programming tasks with native multimodal text and vision input, is now available on Vercel's AI Gateway. The model supports front…
Vercel launched Vercel Drop, a tool that lets users deploy projects by dragging files into a browser without needing Git or CLI setup. The service detects frameworks like Next.js and handles static si…
AI SDK 7 introduces `HarnessAgent`, a unified API that lets developers run established agent harnesses including Claude Code, Codex, and Pi through a single interface. The new abstraction allows users…
Vercel's AI Gateway now supports GLM 5.2, a model with a 1M-token context window designed for long-horizon tasks. The model carries project-level engineering context, runs long-running tasks reliably,…