AI Briefing#sdk
The latest AI and developer news about #sdk, with the original source and a short summary.
The latest AI and developer news about #sdk, with the original source and a short summary.
The SDK connects Unity scenes to ElevenLabs agents via microphone input and AudioSource output, supporting desktop, WebGL, and beta mobile/XR platforms.
The feature uses deployment identity for authentication and requires @flags-sdk/vercel 1.6.0 or later.
The update eliminates network waits during initialization and stops usage reporting from extending function duration.
The update removes sampling parameters from the Messages API and returns 400 errors for documents in assistant turns and citations in user turns.
The update introduces a single background service process, a native JavaScript interpreter for tool orchestration, and asynchronous background subagents.
Snapshot restoration time now counts toward creation, adding about 50 ms to p50 latency but eliminating wait times for the first operation.
The new version enables agents to create their own cron schedules, dynamically reconfigure models and tools per run, and acknowledge Slack messages with reactions.
The API supports decision models like GPT-6 Luna Decisions and requires OpenAI SDK 7.30.0+ (JS) or 3.26.0+ (Python).
Meta has open-sourced code allowing users to build their own Muse AI gadgets using hardware like ESP32 and Raspberry Pi, while also distributing 5,000 pre-built 'Muse Home Link' devices.
Muse has open-sourced its device SDKs and firmware under the Apache 2.0 license, allowing developers to build custom hardware interfaces for the Muse AI assistant using ESP32 and Linux devices.
The new durable_object scheduling policy allows runtime image selection and reduces median startup time to 648ms.
The release of A2A Protocol 1.0 establishes a standard for delegating agent tasks across heterogeneous frameworks.
Europe-based Desert Ant Labs has released 18 specialized small models, including audio and vision, that run on-device without cloud dependency.
Vercel AI Gateway has added asynchronous video generation capabilities via webhooks and polling.
The @vercel/sandbox SDK now supports multi-user and group features, enabling isolated agents to run within a single Sandbox.
Vercel Sandbox now supports a forking feature that creates a new instance by replicating the snapshot and configuration of an existing sandbox.
Vercel Flags has added a real-time evaluation status and metrics view for each flag.
GitHub officially launched the Copilot SDK, which supports 6 programming languages.
When using Vercel Flags in a Vercel deployment environment, automatic authentication is now possible without configuring an SDK Key.
Kaggle has launched a feature that lets users create and run AI benchmark tasks directly from their local development environment.
Introducing Cadenza, a minimal scripting SDK that makes it easy to build AI agents and MCP servers in a .NET 10 environment.
Perplexity is introducing a **Search as Code (SaC)** architecture that leverages search components as code to enable sophisticated search control for AI agents.
It can read the parent issue from Linear and GitHub mentions and call the SDK directly.
Anthropic has acquired Stainless to strengthen Claude's SDK and MCP connectivity.