45 stories · 7d·6 sources covering·30 active storylines
What this is
The Vercel AI SDK is an open-source TypeScript toolkit for building AI apps and agents. shipfeed tracks AI SDK releases, new providers, and streaming and tool-calling features.
is now available on AI Gateway.Grok Imagine Image 2.0 Preview from xAI The model follows detailed instructions closely and plans typography and layout together, so dense, multi-part visuals like infographics, posters…
now supports WebSocket mode for the OpenAI Responses API. You can keep a persistent connection open and continue each turn by sending only new input items plus , instead of re-sending the full context over a fresh HTTP…
You can now run with .Claude Managed AgentsChat SDK Claude Managed Agents handles the agent loop server-side, including the model, tools, session state, and sandboxed web research. Chat SDK gives that agent a chat…
introduces , a single API for running established agent harnesses, including Claude Code, Codex, and Pi. AI SDK has always let you switch models without rewriting your agent. Now you can switch the harness the same…
Patch Changes bae5e2b: fix(security): re-validate tool approvals from client message history before execution The approval-replay path in `generateText`/`streamText` (and `WorkflowAgent.stream`) reconstructed approved…
Patch Changes 1f7f3f5: fix(bedrock): skip passing unsigned reasoning content
With over 20 million monthly downloads and adoption by teams ranging from startups to Fortune 500 companies, the is the leading TypeScript toolkit for building AI applications. It provides a unified API, allowing you…
Using coding agents means setting up multiple accounts, provisioning API keys, and scattering observability and billing. Now, you can route them through to centralize all of this and add controls, with set up in one…
Nimbus builds production AI systems — internal tools, customer agents, retrieval pipelines — combining humans and AI end-to-end. From scoped pilot to production in 4–8 weeks.
can now use as its inference layer and run its agent commands in an isolated microVM. Access 200+ models through AI Gateway at no markup on tokens, and every request appears in your AI Gateway dashboard with the rest…
Terminal coding agents like Claude Code, Codex, and OpenCode can now each run in their own isolated , orchestrated from , a tmux-style manager that runs them side by side in panes. Nothing an agent runs or edits…
You can build human-in-the-loop approvals with Chat SDK through the new subpath. One call posts a card with Approve and Deny buttons and suspends a workflow until someone decides.chat/workflowrequestApprovalWorkflow…
from ByteDance is now available on AI Gateway. It generates up to 30 seconds in a single clip, holding camera movement and continuity without stitching shots together in post. Short clips can also be extended with…
AI Gateway now produces an OpenTelemetry trace for every request. Pro and Enterprise teams can send these traces through Vercel Drains to any OTLP/HTTP-compatible endpoint, including native integrations for Braintrust…
Your eve agent can now navigate the web like a human with .agent-browser The extension gives any agent a full set of browser tools: navigate pages, read content, click, fill forms, take screenshots, and inspect console…
Patch Changes 1659cd5: Prevent validated downloads on Node.js from reaching private or internal services through DNS aliases or DNS rebinding by validating and pinning every resolved address at connection time…
and its faster serving path, , are now available from US-based providers on AI Gateway, including Baseten and Fireworks. (ZDR) is also supported for both models. Kimi K3 from Moonshot AIKimi K3 FastZero Data Retention…
You can now package tools, connections, skills, instructions, and hooks into extensions that any agent can import. Extensions can be published to package registries like npm, then installed, versioned, and upgraded…
Patch Changes 356918c: feat(provider/openai): add GPT-5.6 reasoning and prompt cache controls
now supports .Vercel AI Gatewayrouting rules Routing rules are firewall-style rules that control which models your team can use, applied at the gateway level instead of in your application code. When a model goes down…
gives projects a curated observability view for every agent session in the Vercel dashboard, with no OpenTelemetry setup required.Agent Runseve The Agent Runs tab surfaces the trigger, duration, and token usage for…
Major Changes f7d4f01: feat(provider): add support for `reasoning-file` type for files that are part of reasoning 776b617: feat(provider): adding new 'custom' content type ef992f8: Remove CommonJS exports from all…
Patch Changes 3ee4555: fix(prodia): validate user-supplied image URLs before fetching (SSRF) The Prodia video model's `resolveVideoFileData` fetched a user-supplied `image` URL directly with `fetch()`, bypassing the…
Patch Changes Updated dependencies [19736ee] Updated dependencies [d66ae02] Updated dependencies [e4182bd] ai@7.0.0-canary.166
Patch Changes ce769dd: feat(provider): add experimental Realtime API support for voice conversations Adds first-class support for realtime (speech-to-speech) APIs: `Experimental_RealtimeModelV4` spec in…
Nimbus builds production AI systems — internal tools, customer agents, retrieval pipelines — combining humans and AI end-to-end. From scoped pilot to production in 4–8 weeks.
Chat SDK now supports Twilio, extending its single-codebase approach to Slack, Discord, GitHub, Teams, Telegram, and WhatsApp with the new .Twilio adapter Teams can build SMS and MMS bots that handle direct messages…
Qwen 3.7 Plus from Alibaba is now available on .Vercel AI Gateway The model unifies vision and language into a single agent foundation, with capabilities spanning GUI and CLI operation, coding and productivity…
Qwen 3.7 Max from Alibaba is now available on . The model is designed as an agent foundation, with capabilities spanning coding, office workflow automation, and long-horizon autonomous execution.Vercel AI Gateway Qwen…
Patch Changes 80e1702: feat(xai): support `'none'` and `'medium'` reasoning effort for `grok-4.3`, and curate the model ID autocomplete list `grok-4.3` accepts `reasoning_effort` of `"none" | "low" | "medium" |…
Patch Changes 725f2ed: feat(mcp): expose server instructions to be accessible through client 7281592: fix(mcp): use negotiated protocol version in transport request headers
Patch Changes 4d1b345: feat(provider/moonshotai): own the chat implementation, support video input. The provider no longer builds on `@ai-sdk/openai-compatible`; the converter, language model, and helpers are owned by…